Deep learning framework for multi‐round service bundle recommendation in iterative mashup development

Recent years have witnessed the rapid development of service‐oriented computing technologies.The boom of Web services increases software developers'selection burden in developing new service‐based systems such as mashups.Timely recommending appropriate component services for developers to build new mashups has become a fundamental problem in service‐oriented software engineering.Existing service recom-mendation approaches are mainly designed for mashup development in the single‐round scenario.It is hard for them to effectively update recommendation results according to developers'requirements and behaviours(e.g.instant service selection).To address this issue,the authors propose a service bundle recommendation framework based on deep learning,DLISR,which aims to capture the interactions among the target mashup to build,selected(component)services,and the following service to recommend.Moreover,an attention mechanism is employed in DLISR to weigh selected services when rec-ommending a candidate service.The authors also design two separate models for learning interactions from the perspectives of content and invocation history,respectively,and a hybrid model called HISR.Experiments on a real‐world dataset indicate that HISR can outperform several state‐of‐the‐art service recommendation methods to develop new mashups iteratively.

PRICE AND SERVICE COMPETITION WITH MAINTENANCE SERVICE BUNDLING

In many equipment manufacturing industries, firms compete with each other not only on products price, but also on maintenance service. More and more traditional products oriented finns are offering their customers products bundled with maintenance service （P＆S bundles）. In this study, we examine finns＇ incentive to offer customers products bundling with long-term maintenance or repair support service in a duopoly competitive environment. When providing P＆S bundles, a finn need to determine the service level （in terms of average response time guarantee for the service in this paper） to offer and needs to build a service facility to handle the maintenance service requirements. Based on the analysis of three sub-game models, we characterize the market conditions in which only one firm, both finns or neither finn will offer P＆S bundles. Finally, we analyze the affects of serval market factors on firms＇ strategy choices.

探索生态系统服务对景观变化的响应——以青海省东部为例

The degradation of ecosystem structure and function on the Qinghai-Tibet Plateau is the result of a combination of natural and anthropogenic factors,with landscape change driven by global change and human activities being one of the major ecological challenges facing the region.This study analyzed the spatiotemporal characteristics of ecosystem services(ESs)and landscape patterns in eastern Qinghai province(EQHP)from 2000 to 2018using multisource datasets and landscape indices.Three ecosystem service bundles(ESBs)were identified using the self-organizing map(SOM),and changes in ecosystem structure and function were analyzed through bundle-landscaped spatial combinations.The study also explored the interactions between ESs and natural and human factors using redundancy analysis(RDA).We revealed an increase in total ecosystem service in the EQHP from 1.59 in 2000 to 1.69 in 2018,with a significant change in landscape patterns driven by the conversion of unused land to grassland in the southwest.Forestland,grassland,and unused land were identified as important to the supply of ESs.In comparison to human activities,natural environmental factors were found to have a stronger impact on changes in ESs,with vegetation,meteorology,soil texture,and landscape composition being the main driving factors.However,the role of driving factors within different ESBs varied significantly.Exploring the response of ecosystem services to changes in landscape patterns can provide valuable insights for achieving sustainable ecological management and contribute to ecological restoration efforts.