针对校园网信息检索系统在高并发场景下用户意图识别不准确、信息交互效率低的问题,提出基于改进BERT(Bidirectional Encoder Representations from Transformers)模型的校园网信息动态检索方法。该方法首先通过增强的BERT模型预训练语言表征,结合分类算法优化用户意图识别;其次,设计动态信息交互模块,依据识别出的用户需求类型构建检索模型,并基于检索结果规划信息组织结构;进一步引入NLP技术构建n-gram统计语言模型进行语法校正与自然语言生成,提升输出文本的流畅性与规范性。实验表明,该系统在高并发环境下信息交互准确率达97.5%,显著优于传统方法,实现了高效、稳定的校园网信息动态检索。
Abstract
Aiming at the problems of inaccurate user intention recognition and low efficiency of information interaction in campus network information retrieval system in high concurrency scenarios, this paper proposes a dynamic retrieval method of campus network information based on improved BERT (Bidirectional Encoder Representations from Transformers) model. This method first utilizes an enhanced BERT model for pre-training language representations, combined with classification algorithms to optimize user intent recognition. Next, a dynamic information interaction module is designed to construct a retrieval model based on the identified user needs and organize information according to the retrieval results. Furthermore, an N-gram statistical language model is introduced for grammar correction and natural language generation, improving the fluency and standardization of the output text. Experiments show that the system achieves an information interaction accuracy of 97.5% under high-concurrency conditions, significantly outperforming traditional retrieval methods and enabling efficient and stable dynamic information retrieval on campus networks.
关键词
大规模高并发 /
校园网动态信息 /
信息交互系统 /
BERT模型 /
信息检索
Key words
large-scale high concurrency /
dynamic information on campus network /
information exchange system /
BERT model /
information retrieval
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 彭博. 基于关键词提取的文化遗产信息资源知识抽取方法[J].数字人文研究, 2023(2):39-49.
[2] 邓君,孙绍丹,王阮,等.基于Word2Vec和SVM的微博舆情情感演化分析[J].情报理论与实践,2020,43(8):112-119.
[3] 陈翔,于池,杨光,等.一种基于双重信息检索的Bash代码注释生成方法[J].软件学报,2023,34(3):1310-1329.
[4] Molina-Azorin J F,Guetterman T C.In This Issue:Tribute to Pierre Pluye,Participant Selection Joint Display in Transformative Designs,The Extended Pillar Integration Process,Machine Learning Mixed Methods Text Analysis,and Graphical Retrieval and Analysis of Temporal Information Systems[J].Journal of Mixed Methods Research,2024,18(1):3-5.
[5] 董荣胜,卫晨雨,胡杰,等.基于Bloom分类法的CS1试题数据集的构建及其自动分类[J].计算机科学,2023,50(6):175-182.
[6] Stephane S A,Alfred D D A,Gerard B N,et al.Design of a data storage and retrieval ontology for the efficient integration of information in artificial intelligence systems[J].International Journal of Information Technology,2024,16(3):1743-1761.
[7] 霍朝光,霍帆帆,王婉如,等.基于WordBERT和BiLSTM的政策工具自动分类方法研究[J].图书情报知识,2023,40(3):129-138.
[8] 徐东,王雷,侍守创.基于模糊聚类算法的工业智能应用平台信息自动分类系统设计[J].电子设计工程,2022,30(14):161-164+169.
[9] Mansour R F.Multimodal biomedical image retrieval and indexing system using handcrafted with deep convolution neural network features[J].Journal of Ambient Intelligence and Humanized Computing,2023,14(4):4551-4560.
[10] 史继筠,张驰,李传赫,等.大规模知识图谱数据的分布式存储与检索系统[J].计算机与数字工程,2024,52(2):369-376.
[11] 贺璐倩,王元浩.企业集团档案数字化与信息检索系统的设计与优化[J].中国高新科技,2023(24):126-127+145.
[12] Zhou B.Application of gesture recognition in graphic design and control of information interaction system[J].International Journal of Wireless and Mobile Computing,2023,24(3/4):322-328.
[13] 薛峪峰,田光欣,马占海.基于改进VSM的电力公共信息快速检索系统设计[J].电子设计工程,2023,31(17):46-50.
