重庆工商大学学报:自然科学版
重慶工商大學學報:自然科學版
중경공상대학학보:자연과학판
Journal of Chongqing Technology and Business University:Natural Science Edition
2012年
7期
103-107
,共5页
贾志洋%石宜金%李丁%马瑞英
賈誌洋%石宜金%李丁%馬瑞英
가지양%석의금%리정%마서영
推荐系统%协同过滤%在线教学%教学视频
推薦繫統%協同過濾%在線教學%教學視頻
추천계통%협동과려%재선교학%교학시빈
recommendation system%collaborative filtering%online teaching%teaching video
在目前的在线教学系统中,用户对教学视频的选择具有一定的盲目性,根据这一特点,提出了一种基于协同过滤的在线教学视频推荐方法,可以将用户可能感兴趣的教学视频"推"给用户;首先将用户的观看视频纪录整理并保存至数据库中,依据各用户历史播放纪录以及用户的基本信息的兴趣差异来查询邻居用户,然后利用这些邻居用户的视频观看记录基于协同过滤的方法进行教学视频的推荐;改进了传统协同过滤推荐方法中普遍存在的稀疏性(Sparse)和冷启始(Cold Start)等问题,因此能使推荐更为精确;另外,通过用户是否观看所推荐的视频,可以对系统做出隐性评价以修正系统的参数,以提高推荐的准确性。
在目前的在線教學繫統中,用戶對教學視頻的選擇具有一定的盲目性,根據這一特點,提齣瞭一種基于協同過濾的在線教學視頻推薦方法,可以將用戶可能感興趣的教學視頻"推"給用戶;首先將用戶的觀看視頻紀錄整理併保存至數據庫中,依據各用戶歷史播放紀錄以及用戶的基本信息的興趣差異來查詢鄰居用戶,然後利用這些鄰居用戶的視頻觀看記錄基于協同過濾的方法進行教學視頻的推薦;改進瞭傳統協同過濾推薦方法中普遍存在的稀疏性(Sparse)和冷啟始(Cold Start)等問題,因此能使推薦更為精確;另外,通過用戶是否觀看所推薦的視頻,可以對繫統做齣隱性評價以脩正繫統的參數,以提高推薦的準確性。
재목전적재선교학계통중,용호대교학시빈적선택구유일정적맹목성,근거저일특점,제출료일충기우협동과려적재선교학시빈추천방법,가이장용호가능감흥취적교학시빈"추"급용호;수선장용호적관간시빈기록정리병보존지수거고중,의거각용호역사파방기록이급용호적기본신식적흥취차이래사순린거용호,연후이용저사린거용호적시빈관간기록기우협동과려적방법진행교학시빈적추천;개진료전통협동과려추천방법중보편존재적희소성(Sparse)화랭계시(Cold Start)등문제,인차능사추천경위정학;령외,통과용호시부관간소추천적시빈,가이대계통주출은성평개이수정계통적삼수,이제고추천적준학성。
In current online teaching system, the users have certain blindness on choosing teaching videos, according to this characteristic, online teaching video recommendation method based on collaborative filtering is poi vid nted out, which can recommend the teaching videos in which the users are interested to other users. Firstly, the eo-watehing records are saved in database, and neighboring users are searched based on historic viewing records of each user and the interest difference between each user in basic information, then teaching video recommendation is conducted according to video-watching records of these neighboring users based on collaborative filtering method. This method improves the Sparse and Cold Start commonly existed in traditional collaborative filtering recommendation method and makes the recommendation more accurate. In addition, whether the users watch the recommended videos can make implicit evaluation on the system to revise the parameters of the system and to improve the accuracy of the recommendation.