一种基于知识图谱的文本隐写方法、相关方法及装置

• Format: Patent
• Language: Chinese
• Published: 02.07.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

本发明公开了一种基于知识图谱的文本隐写方法、相关方法及装置，该方法包括根据预先确定的主题匹配的知识图谱中各节点出现的频率，选取频率最高的节点作为起始节点；根据知识图谱对应的图结构，确定起始节点的边集；根据确定的边集中各边的权值，基于哈夫曼树，确定边集中各边的哈夫曼编码；将秘密信息流与边集中各边的哈夫曼编码进行匹配，得到新的起始节点；重复执行确定新的起始节点的边集中各边的哈夫曼编码并与秘密信息流进行匹配的过程，直至秘密信息流编码完成，得到有序链子图；根据预先构建的翻译模型，将有序链子图转换为隐写文本。该方法实现了生成内容的可控性，提高了信息隐藏的安全性和有效性，使隐藏的秘密信息难以检测。 The invention discloses a text steganography method and device based on a knowledge graph, and the method comprises the steps: selecting a node with the highest frequency as an initial node according to the occurrence frequency of each node in a predetermined knowledge graph matched with a subject; determining an edge set of the starting node according to a graph structure corresponding to the knowledge graph; according to the determined weight of each edge in the edge set, on the basis of a Huffman tree, determining a Huffman code of each edge in the edge set; matching the secret information flow with the Huffman code of each edge in the edge set to obtain a new starting node; repeating the process of determining the