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.

A Method for Service-Oriented Personalized Requirements Analysis

The development of Web service has changed the process of software production, and requirements engineering becomes the key issue of service-oriented software engineering. Meantime, it reduces the degree of difficulty of software production, which facilitates end-users to customize software according to their personalized requirements. The paper proposes a method for service-oriented personalized requirements analysis, which is based on domain goal model and process model. The method can inform users of potential errors in requirements by detecting the correctness of requirements, which is driven by users’ personalized operations on goal models, and customize personalized processes to satisfy users’ requirements by reusing domain processes. The personalized processes are the basis for Web service discovery and composition.

An Approach to Generation of Process-Oriented Requirements Specification

In service-oriented computing, process model may serve as a link to connect users’ requirements with Web Services. In this paper, we propose an approach and related key techniques to generate process-oriented requirements specification from user’s goal. For this purpose, a requirements description language named SORL will be provided to capture users’ requirements. Then, a unified requirements meta-modeling frame RPGS will be used to construct reusable domain assets, which is the basis of generating requirements specifications. Finally, a set of rules are defined to extract process control structures from users’ requirements described with SORL, so that we can convert requirements description into process-oriented requirements specification smoothly.

Building Requirements Semantics for Networked Software Interoperability

Naturally, like the web, integrated software systems in Internet will have to be distributed and heterogeneous. To im-prove the interoperability of services for SAAS, it is crucial to build requirements semantics that will cross the entire lifecycle of services especially on requirements stage. In this paper, a requirements semantics interoperability extend-ing approach called Connecting Ontologies (CO) that will act as semantics information carrier designing to facilitate the requirements identification and services composition is proposed. Semantic measurement of Chinese scenario is explored. By adopting the approach, a series of tools support for transport domain are developed and applied based on CO and DPO (Domain Problem Ontology) to enforce requirements engineering of networked software efficiently.

DESIGN METHODOLOGY OF NETWORKED SOFTWARE EVOLUTION GROWTH BASED ON SOFTWARE PATTERNS

Recently, some new characteristics of complex networks attract the attentions of scientist, in different fields, and lead to many kinds of emerging research directions. So far, most of the researcl work has been limited in discovery of complex network characteristics by structure analysis in large-scale software systems. This paper presents the theoretical basis, design method, algorithms and experiment results of the research. It firstly emphasizes the significance of design method of evolution growth for network topology of Object Oriented （OO） software systems, and argues that the selection and modulation of network models with various topology characteristics will bring un-ignorable effect on the process, of design and implementation of OO software systems. Then we analyze the similar discipline of ＂negation of negation and compromise＂ between the evolution of network models with different topology characteristics and the development of software modelling methods. According to the analysis of the growth features of software patterns, we propose an object-oriented software network evolution growth method and its algorithms in succession. In addition, we also propose the parameter systems for OO software system metrics based on complex network theory. Based on these parameter systems, it can analyze the features of various nodes, links and local-world, modulate the network topology and guide the software metrics. All these can be helpful to the detailed design, implementation and performance analysis. Finally, we focus on the application of the evolution algorithms and demonstrate it by a case study. Comparing the results from our early experiments with methodologies in empirical software engineering, we believe that the proposed software engineering design method is a computational software engineering approach based on complex network theory. We argue that this method should be greatly beneficial for the design, implementation, modulation and metrics of functionality, structure and performance in large-scale OO software complex system.