In the digital era, various types of online learning resources have emerged, covering comprehensive fields, providing learners with the opportunity to conveniently access learning resources and flexibly arrange their study time. However, this has also led to drawbacks such as network resource overload and information disorientation, with uneven quality of online resources and little attention to personalized learner needs. As Python has become a popular choice for many beginners and professionals, how to personalize the vast amount of Python learning resources available online has become an urgent issue. This article, based on the advantages of user portraits in resource recommendation services, reviews the shortcomings of current educational resource recommendation services. Taking Python learning resource users as an example, it proposes strategies for optimizing resource recommendation platform services through the process of constructing multi-dimensional Python resource user portraits. The strategies include improving resource quality, personalizing recommended content, diversifying resource formats, speeding up resource recommendations, promptly handling user feedback, establishing a sound protection mechanism, and safeguarding user privacy.

Ju Zhou, Hong Li. Multi-dimensional Model of Python Resources Based on Portrait Technology: Research on Building and Optimizing Recommendation Services. The Frontiers of Society, Science and Technology (2024), Vol. 6, Issue 3: 66-72. https://doi.org/10.25236/FSST.2024.060310.

[1] Ministry of Education. Notice on the Implementation of the "Action Plan for Education Informatization 2.0" [J]. Bulletin of the Ministry of Education of the People's Republic of China, 2018(04): 118-125.

[2] CPC Central Committee and State Council. "China's Education Modernization 2035" [N]. People's Daily, 2019-02-24 (001).

[3] Ministry of Education. Key Points of Work in 2022 [J]. Bulletin of the Ministry of Education of the People's Republic of China, 2022(05): 11-21.

[4] Yin Tingting, Gong Siyi, Zeng Xianyu. Research on Personalized Recommendation Services for Educational Resources Based on User Profiling Technology [J]. Journal of Digital Library Forum, 2019(11): 29-35.

[5] Cooper A, Reimann R R, Cronin D. About Face 3: The Essentials of Interaction Design [M]. New Jersey: Wiley Publishing Inc., 2007: 19-22.

[6] Zheng Baoxin, Zhou Xues ong, Li Bin, et al. Promotion of Mobile Game Products Based on User Profiling and Signaling Mining Technology [C]. Proceedings of the Guangdong Communication Society. Excellent Papers Collection of the 2010 Guangdong Communication Youth Forum [Publisher unknown], 2010: 4.

[7] Song Meiqi, Chen Ye, Zhang Rui. Review of User Profiling Research [J]. Journal of Information Science, 2019, 37(04): 171-177. DOI: 10.13833/j.issn.1007-7634.2019.04.027.

[8] Yang Yan, Sun Tieli, Qiu Chunyan. Research on Personalized Recommendation Technology [J]. Journal of Information Engineering University, 2005(02): 84-87.

[9] Goldberg D, Nichols D. Using collaborative filtering to weave an information tapestry [J]. Communications of the ACM, 1992, 35(12): 61-70.

[10] Resnick P, Varian H R. Recommender systems [J]. Communications of the ACM, 1997, 40(3): 56-58.

[11] Lu Haiming, Lu Zengxiang, Li Yanda. Personalized Network Information Recommendation Based on Multi-Agent Hybrid Intelligence [J]. Computer Science, 2000(07): 32-34.

[12] Ding Lin, Wu Changyong. Application of Data Mining in Personalized Services for Distance Education [J]. E-education Research, 2002(09): 43-46. DOI: 10.13811/j.cnki.eer.2002.09.011.