智能科学与技术学报2025，Vol.7Issue(4)：444-453,10.DOI:10.11959/j.issn.2096-6652.202538
融合K-BERT与KG-BART的测井文本生成方法研究
Research on well logging text generation method combining K-BERT and KG-BART
摘要
Abstract
Well-logging text generation is a key task in oil and gas exploration and development,and its quality directly affects the efficiency and accuracy of subsequent geological structure interpretation.Existing approaches mainly include template-based rule strategies,statistical summarization techniques,and small-scale data-driven models based on recur-rent neural network(RNN)/Transformer architectures.However,these methods generally have problems such as insuffi-cient utilization of domain knowledge,poor contextual and logical consistency in long-text generation,and the absence of multi-task collaborative learning mechanisms.To address the high specialization and complexity of Chinese well-logging texts,this paper proposed a multi-task model,K2-KGLogGen,which integrated the semantic understanding capability of knowledge-enhanced bidirectional encoder representations from transformer(K-BERT)with the text generation strength of knowledge graph-enhanced bidirectional and auto-regressive transformer(KG-BART).The model incorporated a well-logging domain knowledge graph to enhance semantic awareness,used a classification module to provide category-specific contextual guid-ance,and employed a self-attention fusion mechanism to achieve joint optimization of classification and generation.The experi-mental results show that in the classification task,the proposed model achieves significant improvements in F1-score compared to existing mainstream models.Specifically,it outperforms K-BERT(single-task)by approximately 2.2%,BERT by 3.2%,text convolutional neural network(TextCNN)by 4.7%,and support vector machine+term frequency-inverse document frequency(SVM+TF-IDF)by 9.3%.In the generation task,it attains ROUGE-1,ROUGE-2,and ROUGE-L scores of 0.63,0.41 and 0.54,significantly outperforming Transformer,text-to-text transfer transformer(T5),unified language model(UniLM),pointer generator network(PGN),and BART.Ablation studies confirm that the self-attention mechanism and knowledge injection module are key contributors to performance gains.The results demonstrate the effectiveness of K2-KGLogGen in profes-sional well-logging text generation and its potential applicability to other highly specialized technical text generation tasks.关键词
测井文本生成/多任务学习/知识图谱/K-BERT/KG-BART/注意力融合机制Key words
well logging text generation/multi-task learning/knowledge graph/K-BERT/KG-BART/attention fusion mechanism分类
信息技术与安全科学引用本文复制引用
曹茂俊,田明家,肖阳..融合K-BERT与KG-BART的测井文本生成方法研究[J].智能科学与技术学报,2025,7(4):444-453,10.基金项目
国家自然科学基金项目(No.42172161,No.52474035) （No.42172161,No.52474035）
黑龙江省自然科学基金项目(No.ZL2024D003) （No.ZL2024D003）
中国石油科技创新基金项目(No.2024DQ02-0114) （No.2024DQ02-0114）
东北石油大学特色领域团队专项项目(No.2022TSTD-03) The National Natural Science Foundation of China(No.42172161,No.52474035),Heilongjiang Natural Science Foundation Joint Key Projects(No.ZL2024D003),CNPC Innovation Fund(No.2024DQ02-0114),Special Project for Featured Field Teams of Northeast Petroleum University(No.2022TSTD-03) （No.2022TSTD-03）
