Case subject extraction method

The invention provides a case subject extraction method, which comprises the steps of extracting candidate case subjects in each case text in a case corpus based on a PaddleNLP named entity recognition model and an information extraction model, and obtaining key fragments of each candidate case subj...

Full description

Saved in:
Bibliographic Details
Main Authors YANG YITAI, HUANG YALIN, XU JIWEI, DUAN CHUNXIAN, FU ZHUO, WANG JINGPEI, LI YING, ZHANG ZHAOWEN, CHEN SHENGPENG, ZHAO WULING
Format Patent
LanguageChinese
English
Published 11.08.2023
Subjects
CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:The invention provides a case subject extraction method, which comprises the steps of extracting candidate case subjects in each case text in a case corpus based on a PaddleNLP named entity recognition model and an information extraction model, and obtaining key fragments of each candidate case subject based on a trained key fragment extraction model; performing box separation processing on all the key segments to obtain a plurality of key segment boxes; clustering all key segments in each key segment box based on a directed graph merging algorithm to obtain key segments of a plurality of entity categories; and determining a final case subject of each identification category based on the candidate case subject corresponding to each key segment in each entity category. According to the method, the case subject can be automatically extracted from the case text, different descriptions pointing to the same real case subject are classified and unified, the labor expenditure of case information extraction can be re
Bibliography:Application Number: CN202310853155