计算机应用与软件2026，Vol.43Issue(1)：42-49,8.DOI:10.3969/j.issn.1000-386x.2026.01.006
基于多粒度语义匹配的编程任务解决方案推荐
PROGRAMMING TASK-ORIENTED SOLUTION RECOMMENDATION METHOD BASED ON MULTI-GRANULARITY SEMANTIC MATCHING
摘要
Abstract
Existing programming solution recommendation methods either directly ignore the full text of the question or fail to find a suitable way to exert its value,resulting in inaccurate recommendation results.In this paper,we propose MGSMR,a programming task-oriented solution recommendation method based on multi-granularity semantic matching.For a given programming task,MGSMR used the semantic matching model to find relevant question-and-answer discussions as candidate solutions based on two different granularities of the question title and the full text of the question.It further re-ranked the candidate solutions based on the multi-granularity matching method.It combined candidate solutions with external knowledge such as API documentation and third-party libraries to generate recommendation solutions.The evaluation shows that this method outperforms baselines in terms of multiple IR indicators of two datasets by 18%～26%and 2%～4%,andsolution generation can help participants solve programming tasks 23%faster and 22%more accurately.关键词
技术问答/多粒度语义匹配/句向量/稠密段落检索/解决方案生成Key words
Stack Overflow/Multi-granularity semantic matching/Sentence embedding/Dense passage retrieval/Solution generation分类
信息技术与安全科学引用本文复制引用
郁思敏,刘名威,彭鑫,王翀,赵文耘..基于多粒度语义匹配的编程任务解决方案推荐[J].计算机应用与软件,2026,43(1):42-49,8.基金项目
国家自然科学基金项目(61972098). （61972098）
