调查西沙群岛报告书（民国）沈鹏飞

收集完善可能自先秦至民国有关南海诸岛记载的历史古籍，构建南海诸岛典籍AI识别模型，提升古籍刻版文字识别的准确率，实现自古以来南海诸岛相关典籍资料的数字化。中国南海诸岛文献汇编资料库（唐代-民国）共23册著作。

By collecting and completing historical ancient books containing records of the South China Sea Islands ranging from the Pre-Qin Dynasty to the Republic of China, this dataset constructs an AI recognition model for classics related to the South China Sea Islands, improves the accuracy of block-printed text recognition for ancient Chinese books, and realizes the digitization of all relevant classic documents about the South China Sea Islands since ancient times. The China South China Sea Islands Document Compilation Database (Tang Dynasty – Republic of China) consists of 23 volumes of works.

搜集汇总

背景与挑战

背景概述

该数据集是民国时期沈鹏飞关于西沙群岛的调查报告书，时间覆盖0860年至1948年，属于历史古籍文档，主要涉及南海诸岛的历史记载和数字化处理。