T-BOI：一種融合時(shí)間和行為順序信息的序列推薦系統(tǒng)

打開(kāi)文本圖片集

中圖分類號(hào)：TN711-34；TP391.41 文獻(xiàn)標(biāo)識(shí)碼：A 文章編號(hào)：1004-373X（2025）13-0088-08

T-BOI： A sequence recommendation system integrating temporal andbehavioralorderinformation

ZHANG Jing，ZHOU Diao

（CollegeofArtificialIntellgence，NorthChina UniversityofScienceandTechnology，TangshanO63210，China）

Abstract：Recommendation systems basedonuser behavior modelingare widelyused inrecall，sorting，and otherstages， includingsequentialrecommendationsandsesionrecommendations.Inthesequencerecommendation，somebehaviorrecords thatarenotrelatedtothenextbehaviormaybeintroducedduetoexcesivelylongsequencesetingsHowever，thesesion-based recommendation focusesonmediumandshort-termrecommendations，soithaslimitationsincapturinglong-termorgeneral interests.Inviewoftheabove，asequencerecommendationsystem（T-BOl） thatintegratestemporalandbehavioralorder informationhasbeenproposed，makingitsuitableforlong-termandshort-terminterestrecommendations.Intheproposed method，thefeaturerepresentationunitmodule，behaviorweightunitmodule，behaviorsequencerepresentationmodel，and behaviorcategoryoutputunit modulein T-BOIareused to process andobtainthe final predictionresult.The proposed methodis comparedwithsomeadvancedmodels.Thevalidationonpublicdatasetsshowsthat therecommendationsystem hasgood recommendation effect.

Keywords：sequencerecommendation；recommendationsystem；multi behaviorrecommendation;longand short-term preference;position encoding;time information

0 引言

在網(wǎng)絡(luò)高速發(fā)展的時(shí)代，互聯(lián)網(wǎng)用戶在網(wǎng)上留下了大量的歷史行為信息，從這些信息中，往往希望能夠分析出用戶的個(gè)性偏好，以協(xié)助提供更佳的互聯(lián)網(wǎng)服務(wù)。（剩余15189字）