公开(公告)号：US20210397659A1

公开(公告)日：2021-12-23

申请号：US16906077

申请日：2020-06-19

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： CHAO-MIN CHANG ,  Ying-Chen Yu ,  June-Ray Lin ,  KUEI-CHING LEE ,  Curtis CH Wei

IPC: G06F16/955 ,  G06N20/00 ,  G06N5/04 ,  G06F16/951 ,  G06F40/30

Abstract: A computer-implemented method for automatically adjusting a Uniform Resource Locator (URL) seed list. The method includes crawling for documents based on a seed URL list. The method generates relations data from the documents using a Natural Language Processing (NLP) model. The method analyzes the relations data using an auto-seed model. The method modifies the seed URL list.