计算机科学

计算机科学 ›› 2025, Vol. 52 ›› Issue (11A): 240400141-5.doi: 10.11896/jsjkx.240400141

• 数据库&大数据&数据科学 • 上一篇    下一篇

基于用户行为序列特征增强的推荐算法研究

曹天若1, 李景悦2   

  1. 1 国防科技大学 长沙 410000
    2 湖南师范大学 长沙 410012
  • 出版日期:2025-11-15 发布日期:2025-11-10
  • 通讯作者: 李景悦(3371727473@qq.com)
  • 作者简介:1608647231@qq.com

Research on Recommendation Algorithm Based on Embedding User Behavior Sequence Feature Enhancement

CAO Tianruo1, LI Jingyue2   

  1. 1 National University of Defense Technology,Changsha 410000,China
    2 Hunan Normal University,Changsha 410012,China
  • Online:2025-11-15 Published:2025-11-10

PDF (PC)

10

摘要： 随着互联网的迅猛发展,各种功能的APP层出不穷,人们已经可以在互联网上实现各种行为操作,各类商品、新闻、广告等信息流持续不断地产生和传播。与此同时,推荐算法领域的工程师们也在不断收集有用特征来迭代优化算法效果。从早期收集画像特征,演变到用户行为日志和历史行为统计,到目前的用户行为序列特征研究,目前推荐算法领域已取得一套完整的特征工程范式。随着用户的历史行为序列近年来被发现是非常重要的特征。但是,仅凭物品ID能获得的语义嵌入非常有限,也无法自动与其他相关信息进行交叉,其应用在算法效果收益方面也非常有限。自2021年底以来,语言模型的引入在学术界和工业界的应用已取得显著成果,工程师们在推荐算法领域也进行了一些尝试。文中基于语言模型提出了用户行为序列特征增强推荐算法,借助语言模型的语义分析和逻辑思考能力,采用用户行为序列特征的预训练表示学习来实现特征增强,最终提升推荐算法的模型排序能力。

关键词: 推荐算法, 语言模型, 序列特征, 特征增强

Abstract: With the rapid development of the internet,various functional apps have emerged,allowing people to carry out various activities online.All kinds of goods,news,advertisements,and other information continue to be generated and spread on the internet.At the same time,engineers in the field of recommendation algorithms are constantly collecting useful features to iteratively optimize the algorithm’s effectiveness.From early collection of portrait features,evolving to user behavior logs,historical beha-vior statistics,and the current research on user behavior sequence features,the field of recommendation algorithms has now esta-blished a complete feature engineering paradigm.In recent years,it has been discovered that the historical behavior sequence of users is a very important feature.However,the semantic embeddings that can be obtained solely by item IDs are very limited and cannot automatically intersect with other related information,resulting in limited benefits in algorithm effectiveness.Since last year,the introduction of language models has achieved significant results in both the academic and industrial spheres,and engineers in the field of recommendation algorithms have also made some attempts.We propose a recommendation algorithm enhancement based on language models to enhance user behavior sequence features.By leveraging the semantic analysis and logical reasoning ability of language models,pre-training representation learning of user behavior sequence features is used to achieve feature enhancement,ultimately improving the effectiveness of recommendation algorithm models.

Key words: Recommendation algorithm, Language model, Sequence characteristics, Feature augmentation

中图分类号: 

  • TP181
[1]AGRAWAL R,SRIKANT R.Mining sequential patterns[C]//Proceedings of the Eleventh International Conference on Data Engineering.IEEE,1995:3-14.
[2]KULESHOV V,CHAGANTY A,LIANG P.Tensor factorization via matrix factorization[C]//Artificial Intelligence and Statistics.PMLR,2015:507-516.
[3]ZUCCHINI W,MACDONALD I L.Hidden Markov models for time series:an introduction using R[M].Chapman and Hall/CRC,2009.
[4]CHAPELLE O,ZHANG Y.A dynamic bayesian network clickmodel for web search ranking[C]//Proceedings of the 18th International Conference on World Wide Web.2009:1-10.
[5]TAN Y K,XU X,LIU Y.Improved recurrent neural networks for session-based recommendations[C]//Proceedings of the 1st Workshop on Deep Learning for Recommender Systems.2016:17-22.
[6]ZHOU G,ZHU X,SONG C,et al.Deep interest network for click-through rate prediction[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data mining.2018:1059-1068.
[7]ZHOU G,MOU N,FAN Y,et al.Deep interest evolution net-work for click-through rate prediction[C]//Proceedings of the AAAI Conference on Artificial Intelligence,2019,33(1):5941-5948.
[8]FENG Y,LV F,SHEN W,et al.Deep session interest network for click-through rate prediction[J].arXiv:1905.06482,2019.
[9]ZHANG J,ZHENG Y,QI D,et al.DNN-based prediction model for spatio-temporal data[C]//Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems.2016:1-4.
[10]CHENG H T,KOC L,HARMSEN J,et al.Wide & deep lear-ning for recommender systems[C]//Proceedings of the 1st Workshop on Deep Learning for Recommender Systems.2016:7-10.
[11]MCMAHAN H B,HOLT G,SCULLEY D,et al.Ad click prediction:a view from the trenches[C]//Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Disco-very and Data Mining.2013:1222-1230.
[12]COVINGTON P,ADAMS J,SARGIN E.Deep neural networks for youtube recommendations[C]//Proceedings of the 10th ACM Conference on Recommender Systems.2016:191-198.
[13]SUN G F,WU L,LIU Q,et al.Recommendations Based on Collaborative Filtering by Exploiting Sequential Behaviors[J].Journal of Software,2013,24(11):2721-2733.
[14]PI Q,BIAN W,ZHOU G,et al.Practice on long sequential user behavior modeling for click-through rate prediction[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.2019:2671-2679.
[15]MIKOLOV T,CHEN K,CORRADO G,et al.Efficient estimation of word representations in vector space[J].arXiv:1301.3781,2013.
[16]WANG J,HUANG P,ZHAO H,et al.Billion-scale commodity embedding for e-commerce recommendation in alibaba[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.2018:839-848.
[17]WANG L,YANG N,HUANG X,et al.Improving text embeddings with large language models[J].arXiv:2401.00368,2023.
[18]GÜNTHER M,ONG J,MOHR I,et al.Jina embeddings 2:8192-token general-purpose text embeddings for long documents[J].arXiv:2310.19923,2023.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发