面向用户的个性化产品服务系统协同过滤推介方法

doi:10.13229/j.cnki.jdxbgxb.20210964

摘要/Abstract

摘要：

为快速准确地为用户推介新产品服务系统，提出了改进的协同过滤推介模型。首先，确定目标用户邻居集，针对传统协同过滤算法中数据冷启动问题，提出了用户属性相似度和用户体验相似度相结合的方法，并引入Jaccard系数、平均评分修正系数、热门系数，提高用户体验相似度的准确性。其次，确定新产品服务系统相似集，针对传统基于项目的协同过滤算法忽略项目属性对相似性制约的问题，提出了基于产品服务系统属性的改进皮尔逊余弦相似度算法，应用BP神经网络获得不同产品服务系统下各属性的客观权重，提高了属性重要度的可靠性。最后，构建了新产品服务系统的推介准则。以拖拉机产品服务系统推介为例，验证了所提模型的可行性和有效性。

关键词: 农业工程, 产品服务系统, 协同过滤, 皮尔逊相似度, 余弦相似度, BP神经网络, 推介

Abstract:

An improved collaborative filtering recommendation model is proposed to recommend the new product service system for users quickly and accurately. Firstly， the target user neighbor set is determined. Aiming at the problem of data cold start in the traditional collaborative filtering algorithm， a method combining user attribute similarity and user experience similarity is proposed， and Jaccard coefficient， average score correction coefficient and popular coefficient are introduced to improve the accuracy of user experience similarity. Then， the similarity set of new product service system is determined. An improved Pearson cosine similarity algorithm based on product service system attributes is proposed to solve the problem that the traditional project-based collaborative filtering algorithm ignores the similarity constraints of project attributes， and BP neural network is used to obtain the objective weight of each attribute under different product service systems， which improves the reliability of attribute importance. Finally， the recommendation guideline to judge whether the new product service system can be recommended to target user is constructed. Taking the tractor service system recommendation as an example， the feasibility and effectiveness of recommendation model are verified.

Key words: agricultural engineering, product service system, collaborative filtering, Pearson correlation coefficient, cosine similarity, back propagation neural network, recommendation

中图分类号:

TP391.3

吕锋,李念,冯壮壮,张杨航. 面向用户的个性化产品服务系统协同过滤推介方法[J]. 吉林大学学报(工学版), 2023, 53(7): 1935-1942.

Feng LYU,Nian LI,Zhuang-zhuang FENG,Yang-hang ZHANG. Method of collaborative filtering recommendation of personalized product-service system based on user[J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(7): 1935-1942.

图/表 12

图1

表1

表2

图2

图3

表3

表4

表5

表6

表7

表8

表9

参考文献 17

1	孙林岩,李刚,江志斌,等. 21世纪的先进制造模式——服务型制造[J]. 中国机械工程,2007,18(19): 2307-2312.
	Sun Lin-yan, Li Gang, Jiang Zhi-bin, et al. Service-embedded manufacturing: advanced manufacturing paradigm in 21st Century[J]. China Mechanical Engineering, 2007, 18(19): 2307-2312.
2	Xu G Y, Zhang R B, Xu S X, et al. Personalized multimodal travel service design for sustainable intercity transport[J]. Journal of Cleaner Production, 2021,308: No.127367.
3	Zheng P, Lin T J, Chen C H, et al. A systematic design approach for service innovation of smart product-service systems[J]. Journal of cleaner production, 2018, 201(10): 657-667.
4	Jiang L L, Cheng Y T, Yang L. A trust-based collaborative filtering algorithm for E-commerce recommendation system[J]. Journal of Ambient Intelligence and Humanized Computing, 2019, 10(8): 3023-3024.
5	高玉凯,王新华,郭磊,等. 一种基于协同矩阵分解的用户冷启动推荐算法[J]. 计算机研究与发展,2017, 54(8): 1813-1823.
	Gao Yu-kai, Wang Xin-hua, Guo Lei, et al. Learning to recommend with collaborative matrix factorization for new users[J]. Computer Research and Development, 2017, 54(8): 1813-1823.
6	任永功,王瑞霞,张志鹏,等. 基于社交网络能量扩散的协同过滤推荐算法[J]. 模式识别与人工智能, 2021, 34(6):561-571.
	Ren Yong-gong, Wang Rui-xia, Zhang Zhi-peng, et al. Collaborative filtering recommendation algorithm based on energy diffusion in social network[J]. Pattern Recognition and Artificial Intelligence, 2021, 34(6): 561-571.
7	张志鹏,张尧,任永功. 基于覆盖约简的个性化协同过滤推荐方法[J]. 模式识别与人工智能, 2019, 32(7): 607-614.
	Zhang Zhi-peng, Zhang Yao, Ren Yong-gong. Personalized collaborative filtering recommendation approach based on covering reduction[J]. Pattern Recognition and Artificial Intelligence, 2019, 32(7): 607-614.
8	陈碧毅,黄玲,王昌栋,等. 融合显式反馈与隐式反馈的协同过滤推荐算法[J]. 软件学报,2020(3): 794-805.
	Cheng Bi-yi, Huang Ling, Wang Chang-dong, et al. Explicit and implicit feedback based collaborative filtering algorithm[J]. Journal of Software, 2020(3): 794-805.
9	肖诗涛,邵蓥侠,宋卫平,等. 面向协同过滤推荐的新型混合评分函数[J]. 计算机科学,2021, 48(3): 113-118.
	Xiao Shi-tao, Shao Ying-xia, Song Wei-ping, et al. Hybrid score function for collaborative filtering recommendation[J]. Computer Science, 2021, 48(3): 113-118.
10	张润莲,张瑞,武小年,等. 基于混合相似度和差分隐私的协同过滤推荐算法[J]. 计算机应用研究,2021,38(8): 2334-2339.
	Zhang Rui-lian, Zhang Rui, Wu Xiao-nian, et al. Collaborative filtering recommendation algorithm based on mixed similarity and differential privacy[J]. Application Research of Computers, 2021, 38(8): 2334-2339.
11	Feng L, Zhao Q C, Zhou C Q, Improving performances of Top-N recommendations with co-clustering method[J]. Expert Systems with Applications, 2020, 143: 1388-1405.
12	Zhu B, Jin W L, Li L. Evaluation of brake pedal feeling based on subjective and objective comprehensive weighting method[J]. Automotive Engineering, 2021, 43(5): 697-704.
13	Yin Y, Zhang Y. Environmental pollution evaluation of urban rail transit construction based on entropy weight method[J]. Nature Environment and Pollution Technology, 2021, 20(2): 819-824.
14	Liu D G. An entropy weight method of collaborative degree model between producer service industry and manufacturing industry[J]. International Journal of Circuits, Systems and Signal Processing, 2021, 15: 672-676.
15	Xu Z Y, Gao Y B. Kong X Y. Novel Dual-purpose algorithm for principal and minor component analysis[J]. 2020, 8: 31530-31538.
16	陈耶拉,耿秀丽. 基于改进协同过滤的个性化产品服务系统方案推荐[J]. 计算机集成制造系统, 2021, 27(1):240-248.
	Chen Ye-la, Geng Xiu-li. Recommendation of personalized product-service system scheme based on improved collaborative filtering[J]. Computer Integrated Manufacturing Systems, 2021, 27(1): 240-248.
17	吴佳婧,贺嘉楠,王越群,等. 基于项目属性分类的协同过滤算法研究[J]. 吉林大学学报:信息科学版, 2018, 36(4): 470-474.
	Wu Jia-jing, He Jia-nan, Wang Yue-qun, et al. Research on collaborative filtering algorithm based on items' attribute categories[J]. Journal of Jilin University(Information Science Edition), 2018,36(4): 470-474.

相关文章 15

[1]	王斌,何丙辉,林娜,王伟,李天阳. 基于随机森林特征选择的茶园遥感提取[J]. 吉林大学学报(工学版), 2022, 52(7): 1719-1732.
[2]	耿端阳,孙延成,牟孝栋,张国栋,姜慧新,朱俊科. 基于差速辊的青贮玉米籽粒破碎仿真试验及优化[J]. 吉林大学学报(工学版), 2022, 52(3): 693-702.
[3]	温昌凯,谢斌,宋正河,韩建刚,杨倩雯. 拖拉机耐久性加速结构试验设计方法[J]. 吉林大学学报(工学版), 2022, 52(3): 703-715.
[4]	王国伟,朱庆辉,于海业,黄东岩. 基于数字化农机装备的青贮饲料可追溯系统[J]. 吉林大学学报(工学版), 2022, 52(1): 242-252.
[5]	耿端阳,牟孝栋,张国栋,王宗源,朱俊科,徐海刚. 小麦联合收获机清选机理分析与优化试验[J]. 吉林大学学报(工学版), 2022, 52(1): 219-230.
[6]	梁方,王德成,尤泳,王光辉,王宇兵,张晓明,冯金奎. 草地切根施肥补播复式改良机设计与试验[J]. 吉林大学学报(工学版), 2022, 52(1): 231-241.
[7]	王宏志,王婷婷,胡黄水,鲁晓帆. 基于Q学习优化BP神经网络的BLDCM转速PID控制[J]. 吉林大学学报(工学版), 2021, 51(6): 2280-2286.
[8]	杨世军,裴玉龙,潘恒彦,程国柱,张文会. 城市公交车辆驻站时间特征分析及预测[J]. 吉林大学学报(工学版), 2021, 51(6): 2031-2039.
[9]	王新彦,江泉,吕峰,易政洋. 基于参数化模型的零转弯半径割草机侧翻稳定性[J]. 吉林大学学报(工学版), 2021, 51(5): 1908-1918.
[10]	钱震杰,金诚谦,袁文胜,倪有亮,张光跃. 柔性脱粒齿杆与谷物含摩擦打击动力学模型[J]. 吉林大学学报(工学版), 2021, 51(3): 1121-1130.
[11]	程超,付君,陈志,任露泉. 玉米籽粒收获机清选筛堵塞规律及脱附试验[J]. 吉林大学学报(工学版), 2021, 51(2): 761-771.
[12]	丛茜,徐金,马博帅,张晓超,陈廷坤. 基于虚拟仿真的拖拉机后悬挂检测装置设计与实验[J]. 吉林大学学报(工学版), 2021, 51(2): 754-760.
[13]	陈学深,黄柱健,马旭,齐龙,方贵进. 水稻机械除草避苗控制系统设计与试验[J]. 吉林大学学报(工学版), 2021, 51(1): 386-396.
[14]	耿端阳,谭德蕾,于兴瑞,苏国粱,王骞,鹿秀凤,金诚谦. 玉米柔性脱粒滚筒脱粒元件设计与试验[J]. 吉林大学学报(工学版), 2020, 50(5): 1923-1933.
[15]	高锐涛,单建,杨洲,文晟,兰玉彬,张泉勇,汪洋. 植保无人机变量喷雾处方图实时解译系统的设计与试验[J]. 吉林大学学报(工学版), 2020, 50(1): 361-374.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

用户	P₁	P₂	P₃	P₄	用户	P₁	P₂	P₃	P₄
U₁	5	2	5	/	U₅₀	3	/	5	4
U₂	/	/	4	4	U₅₈	3	3	4	/
U₃	2	/	5	3	U₆₄	/	2	5	4
U₆	/	3	5	/	U₆₇	4	/	5	5
U₇	3	/	4	4	U₇₃	5	1	4	/
U₁₂	/	2	5	3	U₇₅	3	/	5	4
U₁₆	4	3	4	/	U₇₈	4	2	5	/
U₁₉	4	/	4	/	U₈₄	4	/	4	3
U₂₂	/	3	5	4	U₈₈	2	3	5	/
U₂₇	4	2	4	/	U₈₉	3	/	5	/
U₃₀	5	/	4	/	U₉₆	4	2	5	3
U₃₄	4	1	5	2	U₉₇	3	/	4	4
U₃₈	3	/	4	4	U₉₈	3	2	4	1
U₄₀	5	3	4	4	U₉₉	3	/	5	2
U₄₅	4	/	4	/	U₁₀₀	4	/	5	4

	m₁	m₂	m₃	m₄	m₅	m₆	m₇	m₈	m₉	m₁₀
P₁	4.5	3.5	4.0	4.2	2.8	3.2	2.5	2.0	2.3	2.4
P₂	3.1	3.5	3.8	4.1	4.5	2.9	3.0	3.7	3.1	2.5
P₃	3.4	4.2	4.6	4.7	2.9	3.8	2.7	3.6	2.6	3.7
P₄	2.7	4.8	4.1	4.0	3.0	3.7	2.3	2.2	3.1	2.9

	m₁	m₂	m₃	m₄	m₅	m₆	m₇	m₈	m₉	m₁₀
P₁	0.1233	0.1063	0.0406	0.1245	0.1186	0.1589	0.1134	0.1823	0.0273	0.0047
P₂	0.0577	0.1221	0.1358	0.1360	0.1389	0.0118	0.0801	0.1385	0.0848	0.1247
P₃	0.0775	0.1129	0.1028	0.1138	0.0556	0.1093	0.1124	0.0924	0.1085	0.0978
P₄	0.1051	0.1210	0.1023	0.0975	0.1215	0.0872	0.0627	0.1021	0.0735	0.1439
P_new	0.1024	0.1170	0.0666	0.1526	0.0360	0.1146	0.1265	0.1027	0.1321	0.0496

	m₁	m₂	m₃	m₄	m₅	m₆	m₇	m₈	m₉	m₁₀
P₁	0.5549	0.3720	0.1624	0.5603	0.3558	0.5085	0.2835	0.3646	0.6020	0.0113
P₂	0.1558	0.4884	0.5568	0.5440	0.4167	0.0437	0.1842	0.3047	0.2629	0.3616
P₃	0.3100	0.4742	0.3701	0.5349	0.1612	0.4153	0.3035	0.3326	0.4232	0.2347
P₄	0.3258	0.4598	0.3887	0.3413	0.3645	0.2529	0.1881	0.3880	0.2279	0.3598
P_new	0.4096	0.4680	0.1998	0.7630	0.1080	0.4584	0.3795	0.3081	0.6605	0.1984