软件导刊2024，Vol.23Issue(12)：66-74,9.DOI:10.11907/rjdk.241778
基于K-BERT-LDA的层级多标签招标标段分类方法
A Hierarchical Multi-Label Bidding Section Classification Method Based on K-BERT-LDA
摘要
Abstract
Traditional manual bidding has low efficiency and accuracy in dividing bids.A hierarchical multi label text classification method based on K-BERT-LDA is proposed for material bidding texts with sparse semantic features and obvious hierarchical structure of labels.First-ly,text features are extracted through a hybrid model.The K-BERT model extracts text features with knowledge injection to compensate for se-mantic information gaps.The LDA topic model extracts topic distribution features and further enriches the text feature representation through feature fusion.Secondly,joint embedding of category labels,where the prediction results of upper level labels can guide lower level classifica-tion and fully utilize the tree structure relationship between labels to improve the accuracy of multi label text classification.Finally,an intelli-gent processing strategy based on text similarity algorithm is proposed to ensure the success rate of bidding and obtain bidding results by merg-ing sections with insufficient pre investment amounts.The experiment shows that the proposed method has better classification performance than other classification methods and single model,and the accuracy,precision and F1 value reach 95.45%,92.57%and 91.88%respectively,which can effectively and accurately achieve the goal of intelligent classification.关键词
招标分标/层级多标签文本分类/知识注入/主题分布/特征融合/文本相似度Key words
bidding division/hierarchical multi-label text classification/knowledge injection/topic distribution/feature fusion/text simi-larity分类
信息技术与安全科学引用本文复制引用
侯继辉,吴小忠,刘晖,夏卓群,梁涤青,邱涵,徐嘉慧..基于K-BERT-LDA的层级多标签招标标段分类方法[J].软件导刊,2024,23(12):66-74,9.基金项目
湖南省自然科学基金项目(2023JJ30052) （2023JJ30052）
