Design and Implementation of Chinese Movie Recommendation System Based on Large Model

DOI: https://doi.org/10.62517/jike.202604308

Author(s)

Ziqian Hu

Affiliation(s)

Guangzhou Southern College, Guangzhou, Guangdong, China

Abstract

Due to the rapid development of Internet video platform and the explosive growth of movie resources, users will inevitably encounter a serious problem of "information overload" when using the platform. At present, the mainstream movie recommendation system can't well tap users' deep interest preferences. However, the large language model has shown excellent performance in semantic understanding, knowledge representation and natural language generation, which points out a very clear new direction for the intelligent upgrade of recommendation system. In this paper, the Chinese film recommendation system based on the big model is designed clearly, and its fundamental purpose is to reasonably combine the semantic understanding ability of the big model with the modern architecture of front-end separation, so as to build an accurate, efficient and easy-to-use Chinese film recommendation platform. Therefore, this paper first introduces five core modules involved in the whole process of user viewing: user management, movie retrieval, personalized recommendation, viewing record management, recommendiation reason display and system management. At the same time, the recommendation engine integrates Chinese big models such as Baidu ERNIE and Deep Seek, and achieves semantic matching between user interests and movie content by means of model fine-tuning and prompt engineering.

Keywords

Large Language Model; Recommendation System; Movie Recommendation; User Portrait; Natural Language Processing

References

[1] Linden G, Smith B, York J. Amazon.com Recommendations: Item-to-Item Collaborative Filtering[J]. IEEE Internet Computing, 2003, 7(1):76-80. [2] Bell R M, Koren Y. Lessons from the Netflix Prize Challenge[J]. SIGKDD Explorations Newsletter, 2007, 9(2):75-79. [3] Cheng H T, Koc L, Harmsen J, et al. Wide & Deep Learning for Recommender Systems[C]. Proceedings of the 1st Workshop on Deep Learning for Recommender Systems, 2016:7-10. [4] He X, Liao L, Zhang H, et al. Neural Collaborative Filtering[C]. Proceedings of the 26th International Conference on World Wide Web, 2017:173-182. [5] Vaswani A, Shazeer N, Parmar N, et al. Attention Is All You Need[C]. Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017:6000-6010. [6] Radford A, Narasimhan K, Salimans T, et al. Improving Language Understanding by Generative Pre-Training[R]. OpenAI, 2018. [7] Devlin J, Chang M W, Lee K, et al. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding[C]. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2019:4171-4186. [8] Lim D, Bae Y, Kim K, et al. XAI-Rec: Explainable Recommendation Using Large-Scale Language Models[C]. Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2023:1842-1846. [9] Netflix Technology Blog. Netflix Recommendations: Beyond the 5 Stars[EB/OL].https://netflixtechblog.com/netflix-recommendations-beyond-the-5-stars-part-1-55838468f429, 2012. [10] Amazon Science. Conversational AI for Prime Video Search[EB/OL].https://www. amazon. science/blog/conversational-ai-for-prime-video-search, 2023. [11] Huang Y C. Design and Implementation of Movie Recommendation System Based on User Profile[J]. Journal of Tongren University, 2023, 25(6):75-83. [12] Chen B Y, Huang L, Wang C D, et al. Collaborative Filtering Recommendation Algorithm Integrating Explicit Feedback and Implicit Feedback[J]. Journal of Software, 2020, 31(3):794-805. [13] Wang Y C. Diversified Movie Recommendation Algorithm Incorporating Trust Factor[J]. Computer Systems & Applications, 2021, 30(12):187-193. [14] Russo C F. LLM-based RecSys: Multi-agent Architectures and Advanced RAG Techniques[D]. Università degli Studi di Padova, 2024. [15] Tung C P L, Haw S C, Kong W E, et al. Movie Recommender System Based on Generative AI[C]. 2024. [16] Xu L, Zhang Z, Wang Z, et al. Prompting Large Language Models for Recommender Systems: A Comprehensive Framework and Empirical Analysis[J/OL]. arXiv preprint, arXiv:2401.04997, 2024. [17] Liu X J, Yuan X C, Liu P C. Top-N Recommendation Algorithm for Item-Based Collaborative Filtering Based on Long Tail Theory[J]. Journal of Qiqihar University (Natural Science Edition), 2019, 35(2): 1-4.