一种基于用户反馈的时间感知推荐方法

将社交网络的动态性和用户反馈信息融入到推荐方法中,提出一种基于用户反馈的时间感知推荐方法。该方法利用时间衰减因子对带有时间加权的动态社交网络进行兴趣衰减分析,使时间间隔较近用户的选择行为对资源对象的推荐作用获得较高的贡献度,体现用户兴趣的时间效应特性。扩展相似度计算方法,将用户反馈表示为正反馈信息和负反馈信息,考虑用户反馈信息对推荐方法的影响。通过在社交网络真实推荐数据集上的对比实验,结果表明该方法优于基于协同过滤的推荐方法。     

Recurrent Tensor Factorization for time-aware service recommendation

With the advent of the era “everything is service ”, the emergence of Web services on the Internet is experiencing an exponential growth trend. How to recommend services to users that utilize sequential historical records has become one of the most challenging research topics in service computing. Tensor Factorization (TF) and Long Short Term Memory (LSTM) networks are two typical application paradigms for sequential service recommendation tasks. However, TF can only learn static short-term dependency patterns between users and services, ignoring the dynamic long-term dependency patterns between users and services. Although LSTM in Deep Leaning can learn dynamic long-term dependency patterns, it often encounters the trouble of vanishing gradient due to its complex gated mechanism. To address these critical challenges, we develop a novel model based on Deep Learning named Recurrent Tensor Factorization (RTF) with three innovations: (1) Three-dimensional interaction tensor of user–service-time was granulated into three fixed-size embedding dense vectors. (2) Personalized Gated Recurrent Unit (PGRU) and Generalized Tensor Factorization (GTF) simultaneously work on shared embedding dense vectors to memorize the long-term and short-term dependency patterns between users and services respectively. (3) Armed with GTF and PGRU, RTF is competent to predict the unknown Quality of Service (QoS) through comprehensive analysis. Experiments are conducted on real-world dataset, and the results indicate that our proposed method obviously outperforms six state-of-the-art time-aware service recommendation methods.     

Integrating web service and semantic dialogue model for user models interoperability on the web

Nowadays there is a great number of Web information systems that build a model of the user and adapt their services according to the needs and preferences maintained by the user model (UM). One of the most challenging issues of this scenario is the possibility to enable different systems to cooperate in order to exchange the available information about a user. Our aim is to create rich (and scalable) communication protocols and infrastructures to enable consumers and providers of UM data to interact. Our solution for dealing with such an issue is to exploit Web standards for interoperability (i.e. Semantic Web and Web Services) for implementing simple atomic communication, and a dialogue model for implementing enhanced communication capabilities. In particular, two systems can start a semantics-enhanced Dialogue Game as a form of negotiation to clarify the meaning of the requested concepts when a shared knowledge model does not exist, and to approximate the response when the exact one is not available. We propose a distributed semantic conversation framework based on the Sesame semantic environment for the exchange of user model knowledge on the Web. Systems have to expose their user model data as a Web Service, and to exploit a public dialogue knowledge base to start the dialogue. The main advantage of the approach is to allow systems to deal with difficult situations by starting an appropriate dialogue game instead of stopping the communication as in the traditional “all-or-nothing” Web Service approach. On the basis of a preliminary evaluation, the approach has shown an improvement of the adaptation results provided by the systems we tested.     

Using information flow analysis to detect implicit information leaks for web service composition

Information leak, which can undermine the compliance of web-service-composition business processes for some policies, is one of the major concerns in web service composition. We present an automated and effective approach for the detection of implicit information leaks in business process execution language (BPEL) based on information flow analysis. We introduce an adequate meta-model for BPEL representation based on a Petri net for transformation and analysis. Building on the concept of Petri net place-based noninterference, the core contribution of this paper is the application of a Petri net reachability graph to estimate Petri net interference and thereby to detect implicit information leaks in web service composition. In addition, a case study illustrates the application of the approach on a concrete workflow in BPEL notation.     

Semantic service provisioning for smart objects: Integrating IoT applications into the web

Internet of Things (IoT) applications residing on the Web are the next logical development of the recent effort from academia and industry to design and standardize new communication protocols for smart objects. This paper proposes the service provisioning architecture for smart objects with semantic annotation to enables the integration of IoT applications into the Web. We aim to bring smart object services to the Web and make them accessible by plenty of existing Web APIs in consideration of its constraints such as limited resources (ROM, RAM, and CPU), low-power microcontrollers, and low-bitrate communication links.     

A time-aware Bayesian approach for optimal manufacturing service recommendation in distributed manufacturing environments

With the growing emergence of distributed collaborative manufacturing systems, the utilization of service-oriented manufacturing to offer seamless access to a variety of complex, distributed and dynamic manufacturing resources has become a challenging issue. This paper presents a novel time-aware probabilistic Bayesian approach for recommending a few optimal manufacturing services based on the user preference for an initial manufacturing service. The Bayesian approach operates over a comprehensive, formal representation of manufacturing services, which adds the time-aware probability of satisfied service execution in manufacturing service ontology to take into account the statistical nature of the dynamic manufacturing environment. The Bayesian approach is useful because it infers a few top ranked hypotheses of manufacturing service that have the largest probability as the optimal selection in a specified context of user preference. A prototype system is built and validated with an illustrative example from manufacturing industry to demonstrate the feasibility of the proposed approach for optimal service recommendation.     

Exploiting two-faceted web of trust for enhanced-quality recommendations

Traditional collaborative filtering (CF) based recommender systems on the basis of user similarity often suffer from low accuracy because of the difficulty in finding similar users. Incorporating trust network into CF-based recommender system is an attractive approach to resolve the neighbor selection problem. Most existing trust-based CF methods assume that underlying relationships (whether inferred or pre-existing) can be described and reasoned in a web of trust. However, in online sharing communities or e-commerce sites, a web of trust is not always available and is typically sparse. The limited and sparse web of trust strongly affects the quality of recommendation. In this paper, we propose a novel method that establishes and exploits a two-faceted web of trust on the basis of users’ personal activities and relationship networks in online sharing communities or e-commerce sites, to provide enhanced-quality recommendations. The developed web of trust consists of interest similarity graphs and directed trust graphs and mitigates the sparsity of web of trust. Moreover, the proposed method captures the temporal nature of trust and interest by dynamically updating the two-faceted web of trust. Furthermore, this method adapts to the differences in user rating scales by using a modified Resnick’s prediction formula. As enabled by the Pareto principle and graph theory, new users highly benefit from the aggregated global interest similarity (popularity) in interest similarity graph and the global trust (reputation) in the directed trust graph. The experiments on two datasets with different sparsity levels (i.e., Jester and MovieLens datasets) show that the proposed approach can significantly improve the predictive accuracy and decision-support accuracy of the trust-based CF recommender system.     

地图符号服务与地图服务的耦合

为了实现地图符号在地图服务(WMS)中的应用,达到灵活定制WMS可视化效果的目的,从支持WMS的图层样式描述规范(SLD)入手,通过对SLD和WMS的分析,研究网络地图符号的发布方法,设计地图符号服务框架,提出了基于SLD,地图符号服务与WMS的耦合方法,以解决基于WMS的WebGIS应用中无法通过符号改变地图可视化效果的问题,实验结果表明该方法可以有效地关联地图符号服务与WMS,实现了WMS可视化效果的灵活定制.     

Quality of service for workflows and web service processes

Workflow management systems (WfMSs) have been used to support various types of business processes for more than a decade now. In workflows or Web processes for e-commerce and Web service applications, suppliers and customers define a binding agreement or contract between the two parties, specifying quality of service (QoS) items such as products or services to be delivered, deadlines, quality of products, and cost of services. The management of QoS metrics directly impacts the success of organizations participating in e-commerce. Therefore, when services or products are created or managed using workflows or Web processes, the underlying workflow engine must accept the specifications and be able to estimate, monitor, and control the QoS rendered to customers. In this paper, we present a predictive QoS model that makes it possible to compute the quality of service for workflows automatically based on atomic task QoS attributes. We also present the implementation of our QoS model for the METEOR workflow system. We describe the components that have been changed or added, and discuss how they interact to enable the management of QoS.     

快速语义Web服务发现方法

针对现有的基于本体描述的语义Web服务发现方法发现效率较为低下的问题,提出一种新的服务发现方法.该方法在基于本体距离计算语义Web服务综合相似度的基础上,利用数据挖掘中的聚类算法AGNES对语义Web服务集合进行聚类预处理,形成若干服务簇,然后应用相应服务发现算法根据相似度阈值定位于某一服务簇内进行查找匹配,从而可减少搜索空间.理论与仿真实验结果表明,该方法既可保证服务发现的准确率,又可明显提高服务发现的效率.     

Computing performance requirements for web service compositions

In order to produce service compositions, modern web applications now combine both in-house and third-party web services. Therefore, their performance depends on the performance of the services that they integrate. At early stages, it may be hard to quantify the performance demanded from the services to meet the requirements of the application, as some services may not be available or may not provide performance guarantees. The authors present several algorithms that compute the required performance for each service from a model of a service composition at an early stage of development. This is also helpful when testing service compositions and selecting candidate web services, enabling performance-driven recommendation systems for web services that could be integrated into service discovery. Domain experts can annotate the model to include partial knowledge on the expected performance of the services. We develop a throughput computation algorithm and two time limit computation algorithms operating on such a model: a baseline algorithm, based on linear programming, and an optimised graph-based algorithm. We conduct theoretical and empirical evaluations of their performance and capabilities on a large sample of models of several classes. Results show that the algorithms can provide an estimation of the performance required by each service, and that the throughput computation algorithm and the graph-based time limit computation algorithm show good performance even in models with many paths.     

Priority scheduling service for E-commerce web servers

Service scheduling is one of the crucial issues in E-commerce environment. E-commerce web servers often get overloaded as they have to deal with a large number of customers’ requests—for example, browse, search, and pay, in order to make purchases or to get product information from E-commerce web sites. In this paper, we propose a new approach in order to effectively handle high traffic load and to improve web server’s performance. Our solution is to exploit networking techniques and to classify customers’ requests into different classes such that some requests are prioritised over others. We contend that such classification is financially beneficial to E-commerce services as in these services some requests are more valuable than others. For instance, the processing of “browse” request should get less priority than “payment” request as the latter is considered to be more valuable to the service provider. Our approach analyses the arrival process of distinct requests and employs a priority scheduling service at the network nodes that gives preferential treatment to high priority requests. The proposed approach is tested through various experiments which show significant decrease in the response time of high priority requests. This also reduces the probability of dropping high priority requests by a web server and thus enabling service providers to generate more revenue.     

An evidence-based scheme for web service selection

Existing studies on the web service selection problem focus mainly on the functional QoS properties of the service rather than the consumer satisfaction and trust aspects. While a good QoS enhances the reputation of a service, different consumers invariably hold differing views of the service contents. Some service reputation approaches primarily consider the consumer’s prior experience of the service via opinion feedback system, may neglect the effect of social trust transition in the recommendations of others. As a result, the problem of reaching consensus on the level of consumer trust regarding service becomes one of key issues in service selection. This study proposes a trust-based service selection model to estimate the degree of consumer trust in a particular service based on the consumers’ direct experience and indirect recommendation of the service. In the proposed approach, the degree of consumer trust is correctly estimated by extending Dempster–Shafer evidence reasoning theory to the reputation computation using consumers’ direct experience and incorporating Jøsang’s belief model for solving the trust transition problem in the indirect recommendation of the service. The proposed model effectively enables deception detection by means of existing bodies of evidence, and therefore excludes the fraudulent evidence of malicious evaluators from the selection process. In addition, a quality index is proposed to help third party (TTP) examine the body of evidence and make the outranking result more reliable. Importantly, the quality index is based not only on the confidence degree of the evidence, but also on the support degree, and therefore discovers the effects of intentional negative assessments. The validity of the proposed approach is demonstrated numerically by means of two service selection examples.     

Deep knowledge-aware framework for web service recommendation

The Journal of Supercomputing - Web services are products in the era of service-oriented computing and cloud computing. Considering the information overload problem arising from the task of...