大数据2025，Vol.11Issue(5)：18-33,16.DOI:10.11959/j.issn.2096-0271.2025058
杉杉:面向高吞吐低延迟服务的计算机公共课问答系统
Shanshan:a question-answering system for computer general courses with high throughput and low latency
摘要
Abstract
The natural language processing capabilities based on large language models have shown wide application potential in intelligent question-answering scenarios.To provide personalized computer learning support for university students,a computer public course question-answering system named"Shanshan"was developed,which was based on a code-oriented large language model.The system was designed with a front-end and back-end separation architecture,and sends user questions to the large language model through a message queue and listens to the model's return results.Leveraging the language understanding and generation capabilities of the large language model,the system was utilized to automatically answer computer-related questions posed by students,and continuous batch processing and retrieval-augmented generation techniques were employed for optimization.Performance evaluation experiments indicated that the system achieved superior performance in terms of concurrency,response time,and multi-turn dialogue compared to alternative methods.关键词
大语言模型/智能问答系统/计算机公共课/批处理/检索增强生成Key words
large language model/intelligent question-answering system/computer public course/batch processing/retrieval-augmented generation分类
信息技术与安全科学引用本文复制引用
杨贇,刘天扬,王硕,苏斌,蒲鹏,陆雪松..杉杉:面向高吞吐低延迟服务的计算机公共课问答系统[J].大数据,2025,11(5):18-33,16.基金项目
国家自然科学基金项目(No.62277017) The National Natural Science Foundation of China(No.62277017) （No.62277017）
