一种面向催化材料领域的文献信息抽取方法  

A literature information extraction method for catalytic materials

作　　者：高强[1] 张仰森[1] 孙圆明 贾启龙 GAO Qiang;ZHANG Yangsen;SUN Yuanming;JIA Qilong(Institute of Intelligent Information Processing,Beijing Information Science&Technology University,Beijing 100192,China)

机构地区：[1]北京信息科技大学智能信息处理实验室,北京100192

出　　处：《北京信息科技大学学报（自然科学版）》2024年第2期50-56,共7页Journal of Beijing Information Science and Technology University

基　　金：北京材料基因工程高精尖创新中心项目。

摘　　要：为有效利用PDF文献中的非结构化文本数据,面向费托合成催化材料领域文献,设计了关键信息抽取流水线从PDF文献中抽取表格及其相应注释等关键信息。以微分二值化网络(differentiable binarization network, DBNet)为基准模型,通过引入自适应空间注意力(adaptive spatial attention, ASA)模块,提出了DB-ASA文本检测模型,提高了检测精度。采用单视觉文本识别模型(scene text recognition with a single visual model, SVTR)进行文本识别,结合领域字典文件在自建数据集上对模型进行微调,文本识别准确率可达93.87%。In order to effectively utilize the unstructured text data in PDF literature in the Fischer-Tropsch synthesis of catalytic materials,a key information extraction pipeline was designed to extract key information such as tables and corresponding annotations from PDF documents.A DB-ASA text detection model was proposed by using the differentiable binarization network(DBNet)as a benchmark model and introducing an adaptive spatial attention(ASA)module,resulting in improved detection accuracy.Using scene text recognition with a single visual model(SVTR)for text recognition,the model was fine-tuned on a self-built dataset by combining domain dictionary files,achieving a text recognition accuracy of 93.87%.

关 键 词：催化材料 费托合成 信息抽取 文本识别 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]