CAJ | 학술논문

为克服传统商品库存成本过大和消费者满意度过低的弊端，采用BP神经网络方法，以超市一段时间内的销售记录为样本数据，分析BP神经网络库存控制模型的训练过程，并验证BP神经网络的自适应能力、容错能力以及处理非线性关系的能力，保证库存预测的准确性，最终提出基于BP神经网络算法的商品库存控制模型。研究结果表明：该控制模型能够准确高效控制超市商品库存，可以为合理控制库存提供决策支持，有效提高库存控制的效率。
위극복전통상품고존성본과대화소비자만의도과저적폐단，채용BP신경망락방법，이초시일단시간내적소수기록위양본수거，분석BP신경망락고존공제모형적훈련과정，병험증BP신경망락적자괄응능력、용착능력이급처리비선성관계적능력，보증고존예측적준학성，최종제출기우BP신경망락산법적상품고존공제모형。연구결과표명：해공제모형능구준학고효공제초시상품고존，가이위합리공제고존제공결책지지，유효제고고존공제적효솔。
In order to overcome the drawbacks of the high traditional inventory costs and low consumer satisfaction, this paper analyzed the training process of BP neural network models of inventory control based on the sales record of a supermarket during a period of time as sample data, and verified that the BP neural network adaptive ability, fault-tolerant ability and the ability of dealing with the nonlinear relationship, ensured the accuracy of inventory forecast, finally proposed the inventory control model based on BP neural network algorithm. The results show that the control model can accurately control the supermarket merchandise inventory, provide decision support for reasonable control of inventory, and improve the efficiency of inventory control.