Chinese Book Keyword Extraction and Generation Algorithm Integrating Title and Topic Attention

In the era of big data, the number and types of book resources are increasing exponentially. However, the existing attribute information of books has a relatively coarse granularity for book descriptions, which not only easily leads users to fall into “information loss” when searching for resources, but also greatly limits the circulation of book resources. In response to the above problems, a Chinese book keyword extraction and generation algorithm that integrates title and subject terms attention (TEG) is proposed, and experiments are carried out on a self-built Chinese book data set. The results show that the improved algorithm has a greater improvement in accuracy, recall and F1 value compared with other comparison algorithms.