Efficient Web APIs Recommendation With Privacy-Preservation for Mobile App Development in Industry 4.0
Wenwen Gong, Wei Zhang, Muhammad Bilal, Yifei Chen, Xiaolong Xu, Weizheng Wang
Abstract
Integrating lightweight web application programming interfaces (APIs) into mobile Apps is a promising way for quick and cost-effective development of mobile Apps with desired functions. Web APIs, on the other hand, are created by distinct enterprises or organizations, making it challenging to develop compatible and diverse mobile Apps by combining existing web APIs. It has been demonstrated that this process is an NP-hard problem. In mobile Apps development, it is often necessary to read confidential information, leading to the business privacy leakage of enterprises. Thus, we devise a novel efficient web APIs recommendation (E-WAR) approach based on locality-sensitive hashing for recommending desirable web APIs to developers. Through analyzing industrial enterprises’ expected needs, E-WAR efficiently makes compatible and diverse web APIs recommendations while guaranteeing privacy protection. Finally, extensive experiments on real-world web APIs datasets are conducted. The results show that E-WAR can achieve significant performance improvements over the existing approaches.