基于超图嵌入表示的商品分仓模型

doi:10.16381/j.cnki.issn1003-207x.2022.0102

Abstract

Abstract:

The rapid development of e-business（EB for short） requires EB companies to respond to consumer requirements quickly， in order to improve their efficiency of customer services， more and more EB companies have deployed distributeddistribution center systems. A main problem with using this system is that improper commodity warehouse allocation may result in a large number of orders being divided into multiple sub-orders， which not only causes inconvenience to customers， but also increases more operating costs to companies. Addressing to this problem， a commodity warehouse allocation model aimed at minimizing the total number of split orders is proposed. The model is based on a hypergraph representation of historic orders， where each vertex corresponds to a distinct goods appearing in the orders， and each hyperedge describes a co-occurrence relation of goods in a same orders. The spectrum decomposition on the Laplace matrix of the hypergraph is performed to obtain the embedding representations of the goods， then a constrained clustering algorithm is proposed and is applied to the above embeddings to generate the allocation results. The comprehensive simulations is conducted to evaluate the proposed model， where LDA （Latent Dirichlet Allocation） with variant parameter settings is used to simulate different ordering behaviors， and the proposed model as well as some other comparison models is applied to generate the allocation results from the data.All experimental results show the superior of our model.

Key words: commodity warehouse allocation, hypergraph, embedding representation, clustering, operations optimization

CLC Number:

TP181

Shun Liu,Xiaoyu Huang,Zhengzheng Xian, et al. A Commodity Warehouse Allocation Model Based on Hypergraph Embedding[J]. Chinese Journal of Management Science, 2024, 32(11): 270-278.

Figures/Tables 11

参数	DS-1	DS-2	DS-3	DS-4
浓度参数 $τ α$	0.0001	0.0001	0.0001	0.0001
浓度参数 $τ β$	0.001	0.003	0.001	0.001
主题个数t	200	200	500	200
泊松强度 $λ$	3.5	3.5	3.5	6
订单总数 $N$	100000	100000	100000	100000
最大长度h	12	12	12	12

品项组	泊松强度 $λ = 3.5$	泊松强度 $λ = 6$
2项组	21348	4531
3项组	25099	9234
4项组	21647	13546
5项组	15367	16428
6项组	8903	16740
7项组	4487	14007
8项组	2007	10480
≥9项组	1142	15034
总数	100000	100000

References 17

1	Seidscher A， Minner S. A Semi-Markov decision problem for proactive and reactive transshipments between multiple warehouses［J］. European Journal of Operational Research， 2013， 230（1）： 42-52.
2	Jasin S， Sinha A. An LP-based correlated rounding scheme for multi-item ecommerce order fulfillment［J］. Operations Research， 2015， 63（6）： 1336-1351.
3	Wang J Z， Huang P 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， New York， USA， August 19-23 ， Association for Computing Machinery， 2018：839-848.
4	Zhang Y， Lin W H， Huang M， et al. Multi-warehouse package consolidation for split orders in online retailing［J］. European Journal of Operational Research， 2021， 289（3）： 1040-1055.
5	Xu P J， Allgor R， Graves S C. Benefits of reevaluating real-time order fulfillment decisions［J］. Manufacturing & Service Operations Management， 2009， 11（2）： 340-355.
6	Andrés C， Marshall F. Assortment allocation to distribution centers to minimize split customer orders［R］. Working Paper， SSRN， 2012..
7	李建斌，李乐乐，黄日环.最小化拆单率的在线零售商多仓商品摆放优化策略研究［J］.管理工程学报，2017，31（3）：167-173.
	Li J B， Li L L， Huang R H. Inventory allocation policy to distribution centers with minimum split orders in online retailing［J］. Jornal of Industrial Engineering/Engineering Management， 2017，31（3）：167-173.
8	李建斌，孙哲，陈威帆，等.面向最小化拆单率的基于订单分配顺序的库存优化研究［J］.工业工程与管理，2017，22（6）：78-84.
	Li J B， Sun Z， Chen W F， et al. Research on inventory optimization for minimizing the rate of separating bills based on the sequence of order distribution［J］. Industrial Engineering and Management，2017，22（6）：78-84.
9	钟丽文，姜同强. 基于改进贪婪关联算法的在线零售商优化拆单问题［J］. 工业工程，2021，24（2）：134-140.
	Zhong L W， Jiang T Q. Online retailer optimal splitting problem based on improved greedy association algorithm［J］. Industrial Engineering Journal，2021，24（2）：134-140.
10	Zhu S， Hu X， Huang K， et al. Optimization of product category allocation in multiple warehouses to minimize splitting of online supermarket customer orders［J］. European Journal of Operational Research， 2021， 290（2）： 556-571.
11	朱姗，张博，胡祥培.“一地多仓”型网上超市多品订单的拆分优化决策方法［J］.中国管理科学，2024， 32（4）： 250-260.
	Zhu S， Zhang B， Hu X P. Order splitting optimization method of multi-item order fulfillment in online supermarkets with multi-warehouses in a city［J］. Chinese Journal of Mangement Science，2024，32（4）： 250-260.
12	胡秉德，王新根，王新宇，等.超图学习综述：算法分类与应用分析［J］.软件学报，2022，33（2）：498-523.
	Hu B D， Wang X G， Wang X Y， et al. Survey on hypergraph learning： Algorithm classification and application analysis［J］. Journal of Software， 2022， 33（2）： 498-523.
13	Zhou D， Huang J， Schölkopf B. Learning with hypergraphs： Clustering， classification， and embedding［C］//Proceedings of the 19th International Conference on Neural Information Processing Systems，Vancouver， British Columbia， Canada， December 4-7， The MIT Press， 2006：1601-1608.
14	Bradley P S， Bennett K P， Demiriz A. Constrained k-means clustering［R］.Working Paper，Microsoft Research，2000.
15	Orlin J B. A polynomial time primal network simplex algorithm for minimum cost flows［J］. Mathematical Programming， 1997， 78（2）： 109-129.
16	Blei D M， Ng A Y， Jordan M I. Latent dirichlet allocation［J］. Journal of Machine Learning Research， 2003， 3（Jan）： 993-1022.
17	Hastie D I， Liverani S， Richardson S. Sampling from Dirichlet process mixture models with unknown concentration parameter： Mixing issues in large data implementations［J］. Statistics and Computing， 2015， 25（5）： 1023-1037.

订单编号	订购商品
D₁	V₂，V₄，V₈
D₂	V₁，V₆，V₇
D₃	V₃，V₅，V₆

数据集	待分仓商品数	0.0005	0.001	0.003	0.005
DS-1	4794	7168	2032	46	0
DS-2	7819	1506	147	0	0
DS-3	7566	3586	376	0	0
DS-4	5234	48439	14077	652	6

算法训练集比例	0.1	0.2	0.3	0.4	0.5	0.6	0.7	0.8	0.9
EMCLS（K=10）	16.13	16.94	16.28	16.72	14.42	14.26	15.15	13.26	13.23
EMCLS（K=30）	12.55	11.07	11.38	11.72	11.16	11.25	11.26	11.41	10.98
EMCLS（K=50）	11.79	11.56	12.12	11.89	12.01	11.59	11.74	11.54	11.57
EMCLS（K=100）	13.68	14.15	14.28	14.54	15.43	13.91	14.04	14.65	13.75
LOOP（HR=0.02）	42.72	42.76	45.18	46.95	46.69	46.78	46.93	46.85	46.93
LOOP（HR=0.05）	39.80	43.15	44.82	44.65	44.37	44.55	44.62	44.46	44.84
LOOP（HR=0.1）	36.83	40.12	40.23	40.30	40.27	40.02	39.92	39.57	39.67
RC	77.29	82.51	83.88	85.31	86.56	87.06	87.47	89.05	88.60

算法训练集比例	0.1	0.2	0.3	0.4	0.5	0.6	0.7	0.8	0.9
EMCLS（K=10）	43.06	39.61	39.85	40.09	39.68	38.25	40.58	39.61	38.76
EMCLS（K=30）	37.79	36.03	35.31	35.98	34.79	35.62	35.46	35.16	34.68
EMCLS（K=50）	36.96	36.18	35.34	35.47	34.72	34.09	34.71	35.01	34.63
EMCLS（K=100）	38.08	37.88	37.73	36.70	36.99	36.19	36.78	37.39	36.44
LOOP（HR=0.02）	75.71	76.08	76.15	76.20	76.15	75.72	75.38	76.05	75.99
LOOP（HR=0.05）	72.09	72.07	71.92	71.91	71.79	71.43	70.72	71.41	71.25
LOOP（HR=0.1）	67.17	66.88	66.78	66.38	66.75	65.87	65.50	66.43	66.02
RC	92.85	92.67	92.73	92.64	92.83	92.56	92.60	92.58	92.93

算法训练集比例	0.1	0.2	0.3	0.4	0.5	0.6	0.7	0.8	0.9
EMCLS（K=10）	40.61	36.41	37.83	37.16	38.44	38.13	37.92	38.41	35.96
EMCLS（K=30）	35.05	32.47	34.09	34.56	33.43	33.38	33.18	33.66	33.43
EMCLS（K=50）	34.34	31.56	32.96	31.39	31.95	31.48	30.83	30.66	31.78
EMCLS（K=100）	34.21	31.80	30.89	31.34	30.36	31.02	30.50	30.12	31.09
LOOP（HR=0.02）	77.52	78.22	78.53	78.42	78.62	78.62	78.47	78.81	79.01
LOOP（HR=0.05）	74.48	75.22	75.12	74.92	74.70	74.83	74.56	74.91	75.41
LOOP（HR=0.1）	69.61	70.17	69.81	69.49	69.71	69.85	69.18	69.47	69.85
RC	92.24	92.94	92.94	92.09	92.90	92.94	92.93	92.76	92.55

A Commodity Warehouse Allocation Model Based on Hypergraph Embedding

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 11

References 17

Related Articles 15

Metrics

Comments

Recommended 0

算法训练集比例	0.1	0.2	0.3	0.4	0.5	0.6	0.7	0.8	0.9
EMCLS（K=10）	22.17	24.82	23.97	25.96	24.09	24.99	23.61	24.04	25.99
EMCLS（K=30）	20.70	20.46	20.79	19.65	19.67	20.03	20.17	20.46	19.05
EMCLS（K=50）	21.34	20.56	21.13	20.17	19.93	20.94	20.98	19.96	21.11
EMCLS（K=100）	24.63	25.96	24.34	24.78	24.26	23.91	25.08	24.17	24.48
LOOP（HR=0.02）	66.72	70.49	70.55	71.02	71.07	70.59	70.70	71.07	70.37
LOOP（HR=0.05）	69.31	69.54	69.54	70.09	70.12	69.47	69.55	70.06	69.26
LOOP（HR=0.1）	66.82	67.42	67.31	67.56	67.44	66.47	66.51	67.23	66.49
RC	94.14	95.74	96.81	96.74	96.98	97.11	96.91	97.24	96.92

[1]	Feng Wang, Lingrong Zhang, Bo Lu. Research on Time-varying Path of Multi-temperature Co-distribution in Cold Chain Logistics Considering Carbon Emissions [J]. Chinese Journal of Management Science, 2025, 33(5): 290-301.
[2]	Qing Yang,Yingxin Bi,Mingxing Chang,Tao Yao. The Impact of Knowledge Transfer among Overlapped Projects on the Program Clustering [J]. Chinese Journal of Management Science, 2024, 32(4): 261-270.
[3]	Qi Zhou,Zhongfei Li,Baijun Deng. Industry Allocation, Clustering Degree and Fund Performance [J]. Chinese Journal of Management Science, 2024, 32(2): 152-165.
[4]	Wei-dong ZHU,Yu-fei TIAN,Fu-wei ZHANG,Xue HU,Xiao-ya DAI. Research on the Relationship between Government Subsidy and SMEs Value Creation from Enterprise Life Cycle Perspective: Based on Rules Mining Using Agglomerative Hierarchical Clustering and Rough Sets [J]. Chinese Journal of Management Science, 2023, 31(8): 80-89.
[5]	LUO Jian, TANG Jia-fu, YU Qing-ya, WU Zhi-qiao. The Division of O2O Takeaway Business Zone and Discovery of Customer Demand Distribution Law [J]. Chinese Journal of Management Science, 2023, 31(3): 58-68.
[6]	GE Xian-long, WEN Peng-zhe, XUE Gui-qin. Two-echelon Dynamic Vehicle Routing Problem with Request Forecasting [J]. Chinese Journal of Management Science, 2022, 30(8): 210-220.
[7]	SUN Yue, QIU Ruo-zhen. Support Vector Clustering-based Data-driven Robust Optimization Model for Multi-product Inventory Problem with Cross-selling [J]. Chinese Journal of Management Science, 2022, 30(2): 156-168.
[8]	CHEN Xi, ZHANG Yi-fei, SUN Ya-ya, LIANG Hai-ming, ZHANG Wen-bo. Research on Clustering and Assignment of Emergency Blood Donors for Emergency [J]. Chinese Journal of Management Science, 2022, 30(12): 77-85.
[9]	NIU Ben, , GUO Chen, TANG Heng. Multi-objective Multi-learning Bacterial Foraging Optimization Algorithm for Mixed Data Clustering [J]. Chinese Journal of Management Science, 2022, 30(12): 131-140.
[10]	HUANG Yi-rong, BAI Yu-xuan. Is It “Intentional Herding” or “Spurious Herding”? The Influence of Network Contagion Degree on the Pricing Efficiency of Capital Market [J]. Chinese Journal of Management Science, 2021, 29(9): 12-24.
[11]	LI Ai-zhong, REN Ruo-en, DONG Ji-chang. Asset Portfolio and Pricing of Multi-factor Matrix Regression under Financial Network Risk [J]. Chinese Journal of Management Science, 2021, 29(6): 1-9.
[12]	MO Dong-xu, ZHENG Tian-dan. Research on Portfolio Optimization Based on Complex Network [J]. Chinese Journal of Management Science, 2021, 29(5): 25-33.
[13]	WANG Ze-zhou, CHEN Yun-xiang, XIANG Hua-chun. Research on an Improved Expert Cluster Weighting Method Based on Fuzzy Kernel Clustering [J]. Chinese Journal of Management Science, 2021, 29(2): 177-183.
[14]	FANG Zhi-geng, GENG Sun-yue, LIU Si-feng, GAO Su, XIE Shi-kun. Clustering Structure Cooperative Working Mechanism Design of Low Orbit Satellite Communication Network Based on Spherical Coordinate System [J]. Chinese Journal of Management Science, 2021, 29(2): 195-204.
[15]	CHEN Heng, LU Wei, DU Lei. Stochastic Evolutionary Scenario Analysis of Risk Set Clustering NIMBY Conflicts Events [J]. Chinese Journal of Management Science, 2020, 28(4): 131-141.