首页> 外国专利> KNOWLEDGE GRAPH CONSTRUCTION METHOD AND APPARATUS, AND COMPUTER DEVICE AND STORAGE MEDIUM

KNOWLEDGE GRAPH CONSTRUCTION METHOD AND APPARATUS, AND COMPUTER DEVICE AND STORAGE MEDIUM

机译:知识图形施工方法和装置,以及计算机设备和存储介质

摘要

The present application relates to the field of knowledge graph drawing of data analysis, and in particular, to a knowledge graph construction method and apparatus, and a computer device and a storage medium. The method comprises: crawling knowledge information of a plurality of webpages to be selected according to seed vocabularies; obtaining an expansion vocabulary according to a skip link; obtaining a vocabulary tag of the seed vocabulary in a webpage to be selected, and constructing a hypernym set; performing word filtering on the expansion vocabularies according to the hypernym set, and obtaining a target word set according to the filtered expansion vocabularies and the seed vocabularies; and constructing a knowledge graph according to the seed vocabularies in the hypernym set and the target word set, the expansion vocabularies and the skip link relationship. According to the knowledge graph construction method, the seed vocabulary data is obtained, skipping and expanding are carried out based on the seed vocabulary data to obtain skipping vocabularies, and moreover, the skipping vocabularies are classified by means of the hypernym set to obtain the target word set, and then the knowledge graph is constructed based on the target word set, so that the construction efficiency is high for special fields.
机译:本申请涉及数据分析的知识图表图谱领域,尤其涉及知识图形施工方法和装置,以及计算机设备和存储介质。该方法包括:根据种子词汇表爬行多个网页的知识信息;根据跳过链接获得扩展词汇;在要选择的网页中获取种子词汇表的词汇标记,并构建高型集;根据HyperNYM集执行扩展词汇表的Word滤波,并根据过滤的扩展词汇表和种子词汇表获得目标字集;并根据HyperNYM集中的种子词汇表和目标字集,扩展词汇表和跳过关系构建知识图。根据知识图形施工方法,获得种子词汇数据,基于种子词汇数据进行跳跃和扩展,以获得跳过词汇,而且,跳过词汇表通过HyperNyM设置为获得目标来分类Word Set,然后基于目标字集构建知识图形,因此特殊字段的构造效率很高。

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号