期刊文献+
共找到5篇文章
< 1 >
每页显示 20 50 100
跨境电商下基于商品属性-情境的推荐算法
1
作者 李建斌 钱自顺 +1 位作者 蔡学媛 戴宾 《系统工程学报》 CSCD 北大核心 2024年第3期333-343,468,共12页
在传统协同过滤推荐算法的基础上,结合跨境电商行业特点,提出了一种基于商品属性和情境权重的混合推荐算法.首先,根据用户商品的历史购买金额和购买次数生成用户偏好评分,并结合用户商品属性相似度和情境化用户相似度得到目标用户的最... 在传统协同过滤推荐算法的基础上,结合跨境电商行业特点,提出了一种基于商品属性和情境权重的混合推荐算法.首先,根据用户商品的历史购买金额和购买次数生成用户偏好评分,并结合用户商品属性相似度和情境化用户相似度得到目标用户的最近邻集,最后将通过变异系数法得到的情境权重纳入评分预测当中,进而生成推荐结果.实证分析表明,本算法能有效提升商品推荐结果的预测准确度,相较基于商品属性的协同过滤推荐算法,本算法可降低商品预测评分平均绝对误差平均达2.72%,提高了跨境电商商品推荐效果.本研究为推荐系统在跨境电商领域的应用提供了新方法. 展开更多
关键词 跨境电商 协同过滤 推荐系统 商品属性 情境权重
下载PDF
高分辨率光程可调水分子光谱参数测量系统及其应用 被引量:2
2
作者 马宏亮 查申龙 +5 位作者 查长礼 张启磊 蔡雪原 曹振松 占生宝 潘盼 《量子电子学报》 CAS CSCD 北大核心 2019年第6期663-669,共7页
基于高分辨率可调谐二极管激光吸收光谱仪(TDLAS)和长程怀特吸收池搭建了一套高分辨率、光程可调吸收光谱测量系统,采用直接吸收光谱技术测量了1.51μm波段(6608~6624.3 cm^-1)水分子室温下的吸收光谱。利用非线性拟合程序,获得了57条... 基于高分辨率可调谐二极管激光吸收光谱仪(TDLAS)和长程怀特吸收池搭建了一套高分辨率、光程可调吸收光谱测量系统,采用直接吸收光谱技术测量了1.51μm波段(6608~6624.3 cm^-1)水分子室温下的吸收光谱。利用非线性拟合程序,获得了57条水分子吸收谱线的线位置、线强和自展宽系数,并与HITRAN2016数据库中的相应数据进行了比较,结果表明整体实验数据与HITRAN 2016符合较好,证明该光谱测量系统适用于水分子吸收谱线参数研究。 展开更多
关键词 光谱学 光谱参数 吸收光谱 水汽 怀特池
下载PDF
集成电路封装课程的教学设计
3
作者 王强 闻军 +1 位作者 蔡雪原 郑江云 《集成电路应用》 2023年第6期154-155,共2页
阐述集成电路封装课程的教学特点,集成电路制造课程的教学模式实践,包括优化课程体系、开展虚拟实验、加强校企合作、完善考核机制。
关键词 集成电路制造 封装技术 课程教学 虚拟实验
下载PDF
Predicting stability of integrated circuit test equipment using upper side boundary values of normal distribution
4
作者 Zhan Wenfa Hu Xinyi +3 位作者 Zheng Jiangyun Yu Chuxian cai xueyuan Zhang Lihua 《The Journal of China Universities of Posts and Telecommunications》 EI CSCD 2024年第2期85-93,共9页
In response to the growing complexity and performance of integrated circuit(IC),there is an urgent need to enhance the testing and stability of IC test equipment.A method was proposed to predict equipment stability us... In response to the growing complexity and performance of integrated circuit(IC),there is an urgent need to enhance the testing and stability of IC test equipment.A method was proposed to predict equipment stability using the upper side boundary value of normal distribution.Initially,the K-means clustering algorithm classifies and analyzes sample data.The accuracy of this boundary value is compared under two common confidence levels to select the optimal threshold.A range is then defined to categorize unqualified test data.Through experimental verification,the method achieves the purpose of measuring the stability of qualitative IC equipment through a deterministic threshold value and judging the stability of the equipment by comparing the number of unqualified data with the threshold value,which realizes the goal of long-term operation monitoring and stability analysis of IC test equipment. 展开更多
关键词 K-means clustering algorithm the upper side boundary of normal distribution THRESHOLD integrated circuit(IC)test equipment stability analysis
原文传递
PRICING STRATEGIES IN A SUPPLY CHAIN WITH MULTI-MANUFACTURER AND A COMMON RETAILER UNDER ONLINE REVIEWS 被引量:4
5
作者 cai xueyuan Li Jianbin +1 位作者 Dai Bin Zhou Tai 《Journal of Systems Science and Systems Engineering》 SCIE EI CSCD 2018年第4期435-457,共23页
Online reviews play an important role in consumer purchasing behavior when shopping online, and in turn affect pricing strategies of sellers. We consider a supply chain consisting of three competitive manufacturers an... Online reviews play an important role in consumer purchasing behavior when shopping online, and in turn affect pricing strategies of sellers. We consider a supply chain consisting of three competitive manufacturers and an e-tailer, which sells multiple substitutable products procured from different manufacturers. Considering reviews in terms of quality information and fit information, we study the effect of online reviews on consumers' purchasing decisions as well as pricing strategies of manufacturers and the e-retailer. Through modelling customer choice with online reviews based on neo-Hoteling model and solving Stackelberg game composed by manufacturers and e-tailer, we obtain the optimal equilibrium prices of manufacturers and the e-tailer. And we distinguish two kinds of effect from online reviews: effect of the opinion bias in product quality and effect of the match informativeness. Furthermore, compared to the case without online reviews, we find online reviews improve a manufacturer's optimal wholesale price, profit as well as the retailer's optimal retailing price, when the adjusted quality revealed by reviews is high; however, online reviews can improve the e-tailer's optimal profit, only when the standard deviation of products' quality revealed by reviews is large enough. Last, we get that the increase of competing manufacturers' quantity would change the dominance between two kinds of effect from reviews on supply chain members. 展开更多
关键词 Online reviews neo-Hoteling model Stackelberg game pricing strategy
原文传递
上一页 1 下一页 到第
使用帮助 返回顶部