we propose a deep-learning-based interactive service recommendation framework named DLISR, which aims to capture the interactions among the target mashup, selected services, and the next service to recommend. Moreover, an attention mechanism is employed in DLISR to weigh selected services when recommending the next service. We also design two separate models for learning interactions from the perspectives of content information and historical invocation information, respectively, as well as a hybrid model called HISR. Experiments on a real-world dataset indicate that HISR outperforms several state-of-the-art service recommendation methods in the online interactive scenario for developing new mashups iteratively.

This work was supported by the National Key Research and Development Program of China under Grant No. 2020AAA0107705 and the National Science Foundation of China under Grant Nos. 61972292 and 62032016. For researchers who are interested in our recommendation algorithm, you can feel free to download and use it as a baseline algorithm. Also, if you think that the algorithm is useful for your work, please help cite the following paper.

Yutao Ma, Xiao Geng, Jian Wang, Keqing He, and Dionysis Athanasopoulos. Deep learning framework for multi-round service bundle recommendation in iterative mashup development. CAAI Transactions on Intelligence Technology, DOI: 10.1049/cit2.12135, 2022.