Software projects are becoming larger and more complicated. Managing those projects is based on several software development methodologies. One of those methodologies is software version control, which is used in the ...Software projects are becoming larger and more complicated. Managing those projects is based on several software development methodologies. One of those methodologies is software version control, which is used in the majority of worldwide software projects. Although existing version control systems provide sufficient functionality in many situations, they are lacking in terms of semantics and structure for source code. It is commonly believed that improving software version control can contribute substantially to the development of software. We present a solution that considers a structural model for matching source code that can be used in version control.展开更多
针对传统编程作业批改效率偏低、主观性突出及现有自动化工具评测维度单一的现实问题,文章构建了融合大语言模型(Large Language Model,LLM)与抽象语法树(Abstract Syntax Tree,AST)的全维度评测系统。该系统借助AST解析提取代码结构特...针对传统编程作业批改效率偏低、主观性突出及现有自动化工具评测维度单一的现实问题,文章构建了融合大语言模型(Large Language Model,LLM)与抽象语法树(Abstract Syntax Tree,AST)的全维度评测系统。该系统借助AST解析提取代码结构特征,结合LLM的语义理解能力,对代码正确性、逻辑完备性及编程规范性进行多维度评估,同时引入知识图谱构建错因归溯与补救建议,依托指令工程生成个性化反馈内容。实验数据显示,该系统在函数题、类与对象题等典型题型中的综合评分准确率达89.1%,反馈有效性平均得分为4.05分,批改效率提升幅度达85%,可助力智能化教学实践。展开更多
文摘Software projects are becoming larger and more complicated. Managing those projects is based on several software development methodologies. One of those methodologies is software version control, which is used in the majority of worldwide software projects. Although existing version control systems provide sufficient functionality in many situations, they are lacking in terms of semantics and structure for source code. It is commonly believed that improving software version control can contribute substantially to the development of software. We present a solution that considers a structural model for matching source code that can be used in version control.
文摘针对传统编程作业批改效率偏低、主观性突出及现有自动化工具评测维度单一的现实问题,文章构建了融合大语言模型(Large Language Model,LLM)与抽象语法树(Abstract Syntax Tree,AST)的全维度评测系统。该系统借助AST解析提取代码结构特征,结合LLM的语义理解能力,对代码正确性、逻辑完备性及编程规范性进行多维度评估,同时引入知识图谱构建错因归溯与补救建议,依托指令工程生成个性化反馈内容。实验数据显示,该系统在函数题、类与对象题等典型题型中的综合评分准确率达89.1%,反馈有效性平均得分为4.05分,批改效率提升幅度达85%,可助力智能化教学实践。
