For distributed recommendation systems built on Spark and Flink big data platforms, when machine learning libraries are used for offline recommendation, Cartesian product calculation will be carried out, which consumes a large amount of memory and causes long algorithm execution time. In real-time recommendation, traditional recommendation algorithm model cannot dynamically sense the interest drift of users, resulting in poor recommendation results. To solve the above problems. This paper introduces the heapsort algorithm into the offline recommendation algorithm to solve the problem that ALS algorithm in MLlib will perform Cartesian product operation in model prediction, which consumes a lot of memory and takes a long time to execute the algorithm. The real-time recommendation algorithm introduces Ebbinghaus forgetting curve, and the fusion of timing weight and reward and punishment factors to dynamically perceive the drift of user interest and generate personalized TOP-N recommendation results. Experimental results show that the execution rate of the offline algorithm adopted in this paper is significantly improved when the RMSE index is basically unchanged. The accuracy rate and recall rate of the real-time recommendation algorithm are significantly improved, and the recommendation results are more in line with users' interests.

Panpan Yang, Guangming Li, Xin Xue. Design of collaborative filtering recommendation algorithm combining time weight and reward and punishment factors. Academic Journal of Computing & Information Science (2022), Vol. 5, Issue 14: 82-87. https://doi.org/10.25236/AJCIS.2022.051413.

[1] PICHL M, ZANGERLE E, SPECHT G. Improving Con-text-Aware Music Recommender Systems: Beyond the Pre-filtering Approach [Z]. Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval. Bucharest, Romania; Association for Computing Ma-chinery. 2017: 201–208.

[2] SCHEDL M, KNEES P, GOUYON F. New Paths in Music Recommender Systems Research [Z]. Proceedings of the Eleventh ACM Conference on Recommender Systems. Como, Italy; Association for Computing Machinery. 2017: 392–393

[3] Goldberg D, Nichols D A, Oki B M, et al. Using collabo-rative filtering to weave an information TAPESTRY[J]. Communications of the ACM, 1992, 35: 61-70.

[4] Paatero P, Tapper U. Analysis of Different Modes of Fac-tor Analysis as Least Squares Fit Problems[J]. Chemo-metrics and Intelligent Laboratory Systems, 1993, 18: 183-194.

[5] Lee D D, Seung H S. Algorithms for non-negative matrix factorization[J]. Advances in Neural Information Pro-cessing Systems, 2001, 13: 2421-2456.

[6] Ma S, Goldfarb D, Chen L. Fixed Point and Bregman It-erative Methods for Matrix Rank Minimization [J]. Math-ematical Programming, 2009, 128: 321-353.

[7] Hinton G E. Rectified Linear Units Improve Restricted Boltzmann Machines Vinod Nair[C]. Proceedings of the 27th International Conference on International Confer-ence on Machine Learning. Santa Fe. New Mexico. 2010. 27. 807-814.

[8] Mishra N, Chaturvedi S, Mishra V, et al. Solving Sparsity Problem in Rating-Based Movie Recommendation Sys-tem[M]. Berlin: Springer-Verlag Press, 2017.

[9] Yu Yonghong, Gao Yang, Wang Hao, et al. Recommendation Algorithm Based on User Social Status and Matrix Decomposition. Journal of Computer Research and Development, 2018, 55 (01): 113-124.

[10] Lu Hang, Shi Zhibin, Liu Zhongbao. Collaborative Filtering Recommendation Algorithm based on User Interest and Rating Difference [J]. Computer Engineering and Applications, 2020, 56 (07): 24-29.

[11] Chen Yuanpeng, Gu Tianlong, Bin Chenzhong, et al. A Scenic spot recommendation method based on Fusion Graph Representation Learning and Sequence Mining [J]. Computer Engineering and Design, 2020, 41 (12): 3563-3569.

[12] Singh A, Sharma D. Evaluation Criteria for Measuring the Performance of Recommender Systems[C]. International Conference on Reliability. IEEE, 2015.

[13] Gao Maoting, Xu Binyuan. Recommendation algorithm based on cyclic neural network [J]. Computer Engineering, 2019, 45(08):198-202.

[14] Feng Yong, Zhang Bei, Qiang Baohua, et al. MN-HDRM: Hybrid Dynamic recommendation model of multi-neural networks with Long and short interest [J]. Chinese Journal of Computers, 2019, 42(01):16-28.

[15] GIRSANG A S, EDWIN A W. Song Recommendation System Using Collaborative Filtering Methods [Z]. Pro-ceedings of the 2019 The 3rd International Conference on Digital Technology in Education. Yamanashi, Japan; Association for Computing Machinery. 2019: 160–162

[16] Qiu Ningjia, Xue Lijiao, He Jinbiao, et al. Application Research of Computers, 2020, 37(10):1-6.

[17] Li Xujun, Yin Zi, LV Qiang. Time Context Collaborative Filtering Recommendation based on Counterfactual Reasoning [J]. Computer Engineering and Design, 2019,42(10):2876-2883.