Content of System Software and Software Engineering in our journal

Published in last 1 year |  In last 2 years |  In last 3 years |  All Please wait a minute... For Selected: Download Citations EndNote Ris BibTeX Toggle Thumbnails Select Code Search Combining Graph Embedding and Attention Mechanism HUANG Siyuan, ZHAO Yuhai, LIANG Yiming Journal of Frontiers of Computer Science and Technology    2022, 16 (4): 844-854.   DOI: 10.3778/j.issn.1673-9418.2010087 The source code retrieval task refers to using natural language as a query statement to search for relevant code fragments in the code base. In code retrieval task, most code retrieval algorithms only consider the text sequence information of the code snippets without considering the structural information of the code, resulting in the inability to fully capture the semantic and grammatical information contained in the code snippets. In order to improve the understanding of programming languages, a code retrieval algorithm (GraphCS) based on the combination of attention mechanism and graph embedding is proposed. In the feature extraction part, LSTM is used to extract the text feature vector representation, and Graph2Vec is used to extract the graph vector feature representation. The attention mechanism is introduced in the feature fusion part to better assign corresponding weights to each feature, thereby improving the understanding of the program. Considering heterogeneous data in source code and natural language, the code fragment features and natural language features are mapped to the same vector space, and ranking loss is used to ensure that the semantically similar points have a closer distance in the feature space. In order to verify the efficiency of the algorithm, it is compared with the best algorithm CODEnn. Experimental results show that there is a certain improvement in Precision@1/5/10, SuccessRate@1/5/10 and MRR. Table and Figures | Reference | Related Articles | Metrics Abstract （548） PDF （291） HTML （65） Select UCTB: Spatiotemporal Crowd Flow Prediction Toolbox CHEN Liyue, CHAI Di, WANG Leye Journal of Frontiers of Computer Science and Technology    2022, 16 (4): 835-843.   DOI: 10.3778/j.issn.1673-9418.2012072 Spatiotemporal crowd flow prediction is one of the key technologies in smart cities. There are mainly two major shortcomings that plague researchers and developers. Firstly, crowd flow is affected by complex factors and previous studies have summarized a variety of spatiotemporal prior knowledge. However, it is difficult for follow-up work to comprehensively incorporate this prior knowledge as its application scenarios are diverse. Secondly, with the development of deep learning technology, implementing state-of-the-art models is cumbersome work and becomes more and more complicated. To fill in the above gaps, this paper designs time-series sampling interfaces and graph construction interfaces. The time series sampling interfaces can generate different types of time series based on diverse prior knowledge, and the graph construction interfaces can build different types of spatial graphs. Moreover, users can extend the above two interfaces to utilize new spatiotemporal prior knowledge. Based on the TensorFlow framework, this paper implements a variety of advanced spatiotemporal graph models and encapsulates the frequently-used spatiotemporal modeling units. Users can leverage state-of-the-art spatiotemporal models and perform customized development based on these advanced layers. In summary, the spatiotemporal crowd flow prediction tool box UCTB integrates diverse spatiotemporal prior knowledge and a variety of advanced models, which may promote the development of spatiotemporal crowd flow prediction applications. The codes and detailed documents are open-source. The URL of UCTB is https://github.com/uctb/UCTB. Table and Figures | Reference | Related Articles | Metrics Abstract （719） PDF （536） HTML （132）