基于主题预测的项目拆分方法、装置、设备及存储介质

本发明涉及人工智能技术，揭露一种基于主题预测的项目拆分方法，包括：获取原始政策文件，对原始政策文件进行段落拆分，得到多个段落，利用预先训练好的标准主题预测模型对多个段落进行主题预测，得到段落对应的主题，将主题相同的段落进行拼接，得到拼接段落，并利用预训练的标题生成模型对拼接段落进行标题生成处理，得到拆分好的项目。此外，本发明还涉及区块链技术，原始政策文件可存储于区块链的节点。本发明还提出一种基于主题预测的项目拆分装置、电子设备以及存储介质。本发明可以提高项目拆分的效率。 The invention relates to an artificial intelligence technology...

Full description

Saved in:
Bibliographic Details
Format Patent
LanguageChinese
Published 25.02.2025
Subjects
CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:本发明涉及人工智能技术，揭露一种基于主题预测的项目拆分方法，包括：获取原始政策文件，对原始政策文件进行段落拆分，得到多个段落，利用预先训练好的标准主题预测模型对多个段落进行主题预测，得到段落对应的主题，将主题相同的段落进行拼接，得到拼接段落，并利用预训练的标题生成模型对拼接段落进行标题生成处理，得到拆分好的项目。此外，本发明还涉及区块链技术，原始政策文件可存储于区块链的节点。本发明还提出一种基于主题预测的项目拆分装置、电子设备以及存储介质。本发明可以提高项目拆分的效率。 The invention relates to an artificial intelligence technology and discloses a project splitting method based on topic prediction. The method comprises the following steps of acquiring an original policy file, performing paragraph splitting on the original policy file to obtain a plurality of paragraphs, performing topic prediction on a plurality of paragraphs by utilizing a pre-trained standard topic prediction model to obtain topics corresponding to the paragraphs, splicing the paragraphs with the same subject to obtain a spliced paragraph, and carrying out title generation processing on the spliced paragraph by utilizing a pre-trained title generation model to obtain a split project. In addition, the invention also relates to a block chain technology, and the original poli
Bibliography:Application Number: CN202111181607