 Research on Intelligent Code Search Technology Based on Deep LearningAnyi Chen Pinnacle Academic Press Proceedings Series, 2025, vol. 2, 137-143 Abstract: The application of code intelligent search technology is gradually becoming a key means to solve the bottleneck of development efficiency in the context of the continuous expansion of software development project scale and the increasing demand for code reuse. This study explores the core applications of deep learning in code search, focusing on semantic representation techniques for code, enhanced semantic matching using Transformer architectures, the use of graph neural networks for code structure parsing, the application of contrastive learning strategies for semantic correlation mining, and the performance of multimodal fusion models in integrating code with natural language descriptions. An innovative intelligent code search system has been developed for system architecture scenarios. It includes the refinement of deep neural network models, the design of retrieval processes based on a dual-tower architecture, and strategies for resource allocation and technology selection during model deployment. Through research, significant progress has been revealed in the complex semantic integration and efficient search of deep learning in code search, opening up new research directions for the development of intelligent code search systems. Keywords: deep learning; code search; code semantics; intelligent search (search for similar items in EconPapers) Downloads: (external link) Related works: Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text Persistent link: https://EconPapers.repec.org/RePEc:dba:pappsa:v:2:y:2025:i::p:137-143 Access Statistics for this article More articles in Pinnacle Academic Press Proceedings Series from Pinnacle Academic Press |
Is your work missing from RePEc? Here is how to contribute.
Questions or problems? Check the EconPapers FAQ or send mail to .
EconPapers is hosted by the
School of Business at Örebro University.