【摘要】：響應速度較慢和推薦內(nèi)容與用戶上下文信息匹配程度低是當前影片推薦系統(tǒng)迫切需要解決的問題。針對上述挑戰(zhàn),提出Spark平臺下基于上下文信息的影片混合推薦方法。它利用分布式并行計算技術(shù)Spark進行加速,來提高系統(tǒng)對于海量數(shù)據(jù)的檢索與計算速度,從而減少了系統(tǒng)響應時間。同時該方法將"上下文推薦"和"交替最小二乘的協(xié)同過濾(ALS)"融合成一種混合推薦方法,提高了系統(tǒng)的推薦精度。實驗結(jié)果表明,所提出的混合推薦方法有不錯的效果。
[Abstract]:Slow response speed and low matching degree between recommendation content and user context information are the urgent problems that need to be solved in the current video recommendation system. In view of the above challenges, this paper proposes a mixed recommendation method based on context information in Spark platform. It uses distributed parallel computing technology (Spark) to speed up the retrieval and computation of massive data, thus reducing the response time of the system. At the same time, the "context recommendation" and "alternating least squares collaborative filtering (ALS)" are combined into a hybrid recommendation method, which improves the recommendation accuracy of the system. The experimental results show that the proposed hybrid recommendation method has a good effect.
【作者單位】： 武漢大學計算機學院軟件工程國家重點實驗室;湖北第二師范學院計算機學院;
【基金】：國家自然科學基金(No.61572374,No.U1135005)
【分類號】：TP391.3
，

本文編號：2208375