基于ZEUS的智能电子商务交易系统设计

传统电子商务系统无法让多个买卖双方就价格、性能、折扣等问题进行即时协商.利用智能体技术实现采购和交易过程的智能化是电子商务系统的发展趋势.ZEUS是基于Java语言的多智能体开发平台和运行环境,并提供了对智能体的管理及通信控制.将ZEUS与电子商务结合,可以构建智能电子商务系统,实现多个买方和卖方的交易协商.描述了ZEUS的工作原理,介绍了基于ZEUS平台设计并实现智能电子商务系统的基本方法,为智能电子商务的实现提供了一种技术途径.     

多智能体协同选择的智能导购模型

基于多智能体协同选择提出了一种导购选择模型,该模型可识别其他可信买方智能体("值得信赖的朋友"),并将它们关于卖方的信息结合自身关于卖方的信息综合起来协同选择质高价低的卖方,从而实现高质量的导购性能。构建了一个存在多种类型的买方和卖方的购物模拟环境,并进行了多组实验。实验结果表明,该模型可以准确地识别可信买方智能体,并可在复杂的购物环境中高效地选择出优质卖方。此外,实验结果还表明,有了该模型,单个买方智能体选择优质卖方的能力要明显高于无多智能体协同选择情况下单个买方智能体的选择能力。     

应急物资采购及代储服务交易的逆向组合拍卖机制设计

建立市场化的政企联合储备模式已经成为应急物资储备体系建设的重要方式.基于此,着眼于应急物资采购及代储服务的交易问题,设计一个逆向组合拍卖机制.在此拍卖机制中,政府是拍卖的买方兼委托人,企业是拍卖的卖方兼竞拍者,应急物资采购及代储服务是拍卖商品.首先,通过一个报童模型建立政府决策行为与拍卖活动之间的关系,并提出企业的投标策略;其次,建立最小化供需偏差和最大化供给数量的竞胜标决定模型;最后,提出一个符合实际背景的数值算例对拍卖机制进行模拟和验证.研究表明,所提出的逆向组合拍卖机制不仅具有经济效率,还能够促进政府一次性达成与多家企业在多个周期的合作.由此可见,运用拍卖机制解决应急物资政企联合储备的交易问题具备理论的优越性和现实的适用性.     

一种基于时间-效用的Agent社会承诺机制

在多Agent系统中,为了完成任务,Agent之间需要建立社会承诺。本文通过将T．Sandholm的分级承诺合同协议思想与时间-效用对协商的影响有机地结合起来,提出了一种基于时间-效用的Agent社会承诺机制,为电子商务环境下存在最大协商时间的一对多协商中的买卖双方Agent之间的社会承诺问题提供了有效的解决方案。文章分析了解除承诺的条件,提出了建立承诺、解除承诺和遵守承诺的规则,从而有效规避了协商中买方Agent与卖方Agent随意达成一致的行为,同时保证了买方Agent能够在最大协商时间内确定最佳交易卖方,从而提高了协商系统的效率和效用。     

七日风云

小型石油工业项目跨入互联网伦敦 BP Amoco 公司以及Apache 公司宣称,两家公司都在一些小型交易中采用了互联网,并获得了满意的结果。两家公司还有可能会借助网络进行交易。石油工业除了建立采购产品设备以及能源商品交易站点之外,最近也建立了石油以及天然气资产交易站点。     

基于B/S三层结构、C/S两层结构的网上竞价系统

随着网上交易、网上生活的电子商务时代到来,通过计算机网络将买方和卖方的信息、产品和服务联系起来。网上竞价系统就是基于该思想的一种反向拍卖系统,在适当的情况下,最大限度地激发卖方的竞价热情,从而使买方获得尽可能低的采购成本。     

基于智能Agent的电子商务知识管理

通过运用智能Agent技术解决了客户知识获取的问题.建立了基于智能Agent的电子商务知识管理框架,运用买方Agent获取客户知识,卖方Agent检索相匹配的产品信息;还运用ontology对产品和客户进行建模,并构造了基于ontology的产品分类学习算法.最后,通过原型的验证证明智能Agent技术能够有效地获取客户知识,也提高了产品信息检索的精度与速度.研究结果为电子商务环境下的客户知识管理提供了新思路.     

基于RESTful的校园二手商品交易系统的设计与实现

针对传统校园二手商品交易的不足,结合高校特定区域的优势以及RESTful架构风格的特性,提出基于RESTful的校园二手商品交易系统。对系统进行总体架构、功能模块、数据库以及RESTful API设计,运用Python语言、ORM技术以及Flask框架,实现了系统的商品发布、商品分类展示、商品搜索、商品交易等主要功能。实际测试与应用结果表明,该系统运行比较稳定,具有较强的扩展性,能够较好地满足大学生进行闲置物品交易的需求。     

基于JADE的智能电子商务系统设计

传统电子商务系统无法让买卖双方就价格、性能、折扣等问题进行即时协商.利用智能体技术实现交易过程智能化是电子商务系统的发展趋势.JADE是基于Java语言的多智能体开发和运行环境,提供了对智能体的管理及通信控制.将JADE与Web访问技术结合起来,可以方便地构建智能电子商务系统,实现买方和卖方的交易协商.描述了JADE的工作原理,介绍了基于JADE平台设计并实现智能电子商务系统的基本方法,为智能电子商务的实现提供了一种技术途径.     

C2C交易中卖方信用评价因素研究*

随着互联网上电子商务的高速发展,越来越多的商品销售方进入C2C这一行业,一方面促进了网络交易的繁荣,另一方面也增加了买方合理选择良好交易对象的难度。分析能够反映卖方信息的指标因素,使用自定义的网络数据抓取工具,随机选取40条卖方的指标数据用做分析。使用主成分分析法对这些卖方的信用指标进行计算和处理,并对结果进行分析,提取出影响信用选择的主要因素,最终得到13项对信用评价起重要作用的评价因素;应用该方法对卖方进行评价得到评价排序,为区分和筛选不同信用程度的卖方信息提供了参考。     

The trust model of enterprise purchasing for B2B e-marketplaces

Electronic commerce and online marketplaces have rapidly become critical transaction channels. Many studies of online marketing have focused on the purchasing behaviors of general buyers. However, many business to business (B2B) e-marketplaces allow professional procurement personnel from various businesses to electronically search for and purchase commodities; this facilitates price referencing and helps procurement personnel complete the tasks associated with direct purchasing functionalities. Despite this trend, few studies have examined the purchasing behavior of procurement personnel in B2B e-marketplaces. To fill this research gap, this study examines the relationships between trust in intermediaries and sellers; trust in commodity information; and the online purchase intentions of the procurement personnel in B2B e-marketplaces. This study also investigates the mediating effect of perceived value on the relationship between trust in commodity information and online purchase intention. The results indicate that the relationship between trust in commodity information and online purchase is mediated by perceived value. In addition, both intermediary trust and seller trust positively and significantly influence trust in commodity information, and intermediary trust positively influences seller trust. This finding is a valuable reference for professionals working in B2B e-marketplaces.     

基于Spring MVC的大数据交易集市平台

传统的大数据交易集市以促成大数据交易为主, 类似普通商品交易平台, 提供的主要功能偏重于数据目录管理、交易过程的事务管理. 这种方式存在诸多弊端, 除公开数据外, 各数据所有者考虑到数据安全、隐私或数据被滥用, 或分享数据损害自身竞争优势, 仍对数据交换持谨慎态度, 同时各企业对不同行业、多领域存在的数据了解有限, 制...     

一种安全可行的数字水印协议

针对已提出的数字版权维护协议中存在的买方频繁参与交易,以及过多第三方参与的问题,提出一种安全高效的数字水印协议。该协议引入具有同态性的Paillier加密算法以及虹膜识别技术,解决了匿名、未绑定、盗版追踪等相关安全问题。并且交易过程中参与方之间的通信数据均采用加密、数字签名认证等形式表示,以确保通信数据的保密性与完整性。除此之外,买方选用交易应用程序完成信息传递、购买的操作,使得协议更加贴近日常的交易模式,易于实现。     

基于多级客户模型的个性化推荐机制

个性化是未来Web智能系统的一大特征．为了实现商品的个性化推荐，提出了一种新的基于多级客户模型的推荐系统机制，它由数据准备、模型学习、推荐集的生成和智能过滤四个子过程构成．该机制借助于多级客户模型从客户的购物需求、偏爱特征和消费能力三方面捕获客户的实际需求，从而实现了一种深层次的个性化推荐，改善了推荐效果．     

Intelligent stock trading system with price trend prediction and reversal recognition using dual-module neural networks

This article presents an intelligent stock trading system that can generate timely stock trading suggestions according to the prediction of short-term trends of price movement using dual-module neural networks(dual net). Retrospective technical indicators extracted from raw price and volume time series data gathered from the market are used as independent variables for neural modeling. Both neural network modules of thedual net learn the correlation between the trends of price movement and the retrospective technical indicators by use of a modified back-propagation learning algorithm. Reinforcing the temporary correlation between the neural weights and the training patterns, dual modules of neural networks are respectively trained on a short-term and a long-term moving-window of training patterns. An adaptive reversal recognition mechanism that can self-tune thresholds for identification of the timing for buying or selling stocks has also been developed in our system. It is shown that the proposeddual net architecture generalizes better than one single-module neural network. According to the features of acceptable rate of returns and consistent quality of trading suggestions shown in the performance evaluation, an intelligent stock trading system with price trend prediction and reversal recognition can be realized using the proposed dual-module neural networks.     

An intelligent hybrid trading system for discovering trading rules for the futures market using rough sets and genetic algorithms

Discovering intelligent technical trading rules from nonlinear and complex stock market data, and then developing decision support trading systems, is an important challenge. The objective of this study is to develop an intelligent hybrid trading system for discovering technical trading rules using rough set analysis and a genetic algorithm (GA). In order to obtain better trading decisions, a novel rule discovery mechanism using a GA approach is proposed for solving optimization problems (i.e., data discretization and reducts) of rough set analysis when discovering technical trading rules for the futures market. Experiments are designed to test the proposed model against comparable approaches (i.e., random, correlation, and GA approaches). In addition, these comprehensive experiments cover most of the current trading system topics, including the use of a sliding window method (with or without validation dataset), the number of trading rules, and the size of training period. To evaluate an intelligent hybrid trading system, experiments were carried out on the historical data of the Korea Composite Stock Price Index 200 (KOSPI 200) futures market. In particular, trading performance is analyzed according to the number of sets of decision rules and the size of the training period for discovering trading rules for the testing period. The results show that the proposed model significantly outperforms the benchmark model in terms of the average return and as a risk-adjusted measure.     

A hybrid stock trading system for intelligent technical analysis-based equivolume charting

This paper presents the use of an intelligent hybrid stock trading system that integrates neural networks, fuzzy logic, and genetic algorithms techniques to increase the efficiency of stock trading when using a volume adjusted moving average (VAMA), a technical indicator developed from equivolume charting. For this research, a neuro–fuzzy-based genetic algorithm (NF-GA) system utilizing a VAMA membership function is introduced. The results show that the intelligent hybrid system takes advantage of the synergy among these different techniques to intelligently generate more optimal trading decisions for the VAMA, allowing investors to make better stock trading decisions.     

Modeling and optimization of two-stage procurement in dual-channel supply chain

An online marketing platform should be designed to fairly take the benefits of buyers and suppliers into consideration based on their risk preferences and business strategies. In this paper, the dual-channel supply chain models are developed to implement the risk-averse strategy for buyers and risk-neutral strategy for suppliers, respectively. The buyers under the consideration are the manufacturers who acquire raw materials, parts, or components to make their final products. The major factors in the developed models include the risk preferences of buyers and suppliers, random price fluctuations of goods, and varying demands of final products. To reflect the purchasing practice of a manufacturer, (1) a supply chain is considered to have two supply channels, i.e., contract-based purchase with a lead-time before the goods are used and a direct purchase from online spot markets when the goods are used; (2) the time factor on decision making is specially taken into account, and the procurements are divided into the contract stage of purchase and online stage of purchase. Gaming analysis is conducted to develop the supply chain models for manufactures and suppliers to implement their purchasing or pricing strategies. The simulation is conducted and the result has shown that two-stage purchases in a dual-channel supply chain have improved the performances of suppliers and manufacturers in terms of the profits they can make, their supply–demand relations, and their adjustability to uncertainties in globalized and segmented markets. The proposed model has its significance for manufacturers to better control the price risk of goods and the demand risk of final products; on the other hand, suppliers can benefit from adjusting dynamic sales using online spot markets.     

基于多代理的分布式智能电子商务系统设计

传统电子商务系统结构比较单一,一般是由若干个固定的服务器组成,每个服务器提供固定功能的服务,这样就限制了系统的安全性和鲁棒性的提高。同时,系统的交易形式不够灵活,无法让交易双方在任意时间就商品的价格、折扣和交易时间等问题进行即时协调和协商,以达到尽最大努力促使交易成功,从而达到双赢的目的。针对以上问题,本文提出了基于多代理的分布式智能电子商务系统设计,即利用多代理技术实现系统结构的分布式设计和交易过程的智能化,让智能代理按照客户的意愿自动地帮助客户进行交易商品的查询、谈判和交易。本方法不仅有效地提高了系统的鲁棒性、安全性和健壮性,而且促进了系统向智能化方向发展。最后利用JADE平台实现系统,从而证明了实现方案的可行性。     

遗传BP神经网络在大宗商品市场风险预警中的应用

研究利用遗传BP神经网络预警大宗商品电子交易市场风险的应用方法,将定量分析的思维方式引入大宗商品市场风险评价管理中.为此目的,建构了一个基于遗传BP神经网络的预警模型（GA-BPNNM）,在市场调研的基础上建立了大宗商品电子交易市场风险评价指标体系,并通过实验确定了预警模型的最佳训练函数和隐层的最佳节点数.GA-BPNNM借助BP神经网络强大的自学习能力和非线性映射能力,克服传统手段在分析大宗商品电子交易市场风险时因其定义的模糊性和诱发因素的多样性所带来的困难;同时通过遗传算法与BP网络两者相互融合优化,解决BP神经网络易落入局部最优、收敛速度慢以及遗传算法易早熟等问题.仿真测试实验表明,GA-BPNNM预测结果优于标准BP神经网络预测方法,用于大宗商品电子交易市场风险损失程度预警是有效可行的.