• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2021.11a
• /
• pp.109-111
• /
• 2021

IT를 기반으로 하는 상거래 시장은 COVID-19와 맞물려 많은 변혁이 오고 있다. 과거 오프라인에서 주로 소비되던 생필품이 전자상거래 시장으로 이동하는 등 COVID-19 이후 온라인 구매 전환이 더욱 확대 강화될 것으로 보인다. 그로인해 물류센터를 운영하는 물류기업 또한 과거 하역 및 하역에 수반하는 보관중심의 전통적 물류기능만을 고수하기에는 변화되는 트랜드가 너무 급박하여 기업의 존립까지도 위협을 받을 수 있다. 이에 본 연구에서는 항만의 미래 생존전략을 위해 전자상거래 시대의 환경변화에 빠르게 대응할 수 있도록 국가간 전자상거래 기반 부산항의 풀필먼트센터 구축 당위성과 전환수요 등을 도출하였다.

• The Journal of Bigdata
• /
• v.6 no.2
• /
• pp.17-28
• /
• 2021

Current development of technologies related to 4^th industrial revolution and the pandemic of COVID-19 lead the rapid expansion of e-marketplace. The level of competition among several companies gets increased by introducing different strategies. To cope with the current change in the market and satisfy the customers who request the better delivery service, the new concept, fulfillment, has been introduced. It makes the leadtime of process from order picking to delivery reduced and the efficiency improved. Still, the efficiency of operation in fulfillment centers constrains the service level of the entire delivery process. In order to solve this problem, several different approaches for demand forecasting and coordinating supplies using Bigdata, IoT and AI, which there exists the trivial limitations. Because it requires the most lead time for operation and leads the inefficiency the process from picking to packing the ordered items, the logistics service providers should try to automate this procedure. In this research, it has been proposed to develop the efficient plans to automate the process to move the ordered items from the location where it stores to stage for packing using AGV and AMR. The efficiency of automated devices depends on the number of items and total number of devices based on the demand. Therefore, the result of simulation based on several different scenarios has been analyzed. From the result of simulation, it is possible to identify the several factors which should be concerned for introducing the automated devices in the fulfillment centers. Also, it can be referred to make the optimal decisions based on the efficiency metrics.

• The Journal of Bigdata
• /
• v.8 no.2
• /
• pp.149-163
• /
• 2023

Due to the continuous growth of the E-commerce market, the volume of orders that fulfillment centers have to process has increased, and various customer requirements have increased the complexity of order processing. Along with this trend, the operational efficiency of fulfillment centers due to increased labor costs is becoming more important from a corporate management perspective. Using historical performance data as training data, this study focused on real-time box recommendations applicable to packaging areas during fulfillment center shipping. Four types of data, such as product information, order information, packaging information, and delivery information, were applied to the machine learning model through pre-processing and feature-engineering processes. As an input vector, three characteristics were used as product specification information: width, length, and height, the characteristics of the input vector were extracted through a feature engineering process that converts product information from real numbers to an integer system for each section. As a result of comparing the performance of each model, it was confirmed that when the Gradient Boosting model was applied, the prediction was performed with the highest accuracy at 95.2% when the product specification information was converted into integers in 21 sections. This study proposes a machine learning model as a way to reduce the increase in costs and inefficiency of box packaging time caused by incorrect box selection in the fulfillment center, and also proposes a feature engineering method to effectively extract the characteristics of product specification information.

• The Journal of Society for e-Business Studies
• /
• v.26 no.1
• /
• pp.67-78
• /
• 2021

The number of domestic e-commerce transactions has been breaking its own record by an annual average growth rate of over 20% based on volume for the past 5 years. Due to the rapid increase in e-commerce market, retail companies that have difficulty meeting consumers in person are in fierce competition to take the lead in the last mile service, which is the only point of contact with customers. Especially in the delivery area, where competition is most intense, the role of the fulfillment center is very important for service differentiation. It must be capable of fast product preparation ordered by consumers in accordance with the delivery service level. This study focuses on the order picking system for rapid order processing in the fulfillment center as an alternative for companies to gain competitive advantage in the e-commerce market. A mixed integer programming model was developed and implemented to optimize the stock replenishment in order picking facilities. The effectiveness was scientifically and objectively verified by simulation using the actual operation process and data.

• The Journal of Bigdata
• /
• v.6 no.1
• /
• pp.1-12
• /
• 2021

The rapid growth of mobile-based online shopping and the appearance of untact business initiated by COVID-19 has led to an explosive increase in demand for logistics services such as delivery services. In order to respond to the rapidly growing demand, most logistics and distribution companies are working to improve customer service levels through the establishment of a full-filament center in the city center. However, due to social factors such as high land prices and traffic congestion, it becomes more difficult to establish the logistics facilities in the city center. In this study, it has been proposed the way to choose the candidate locations for the shared distribution centers among the space nearby the tall-gate which can be idle after the smart tolling service is widely extended. In order to evaluate the candidate locations, it has been evaluated the centralities of all candidates using social network analysis (SNA). To understand the result considering the characteristics of centrality, the network structure was regenerated based on the distance and the traveling time, respectively. It is possible to refer the result of evaluation based on the cumulative relative importance to choose the best set of candidates.