Image information extraction method and device based on pre-training language model

The invention belongs to the technical field of natural language processing, and provides an image information extraction method and device based on a pre-training language model, and the method comprises the steps: building a prompt library, and constructing a prompt structure template based on a p...

Full description

Saved in:
Bibliographic Details
Main Authors CUI WEI, JIA ZHIQIANG, ZHAO JINGKUN, FU CHENG, WANG XINYU, NIU GUANJIE, JIN XING
Format Patent
LanguageChinese
English
Published 10.10.2023
Subjects
CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:The invention belongs to the technical field of natural language processing, and provides an image information extraction method and device based on a pre-training language model, and the method comprises the steps: building a prompt library, and constructing a prompt structure template based on a problem type and an application scene; inputting a to-be-processed character picture, and identifying character elements and coordinate position information of each character element; selecting an adaptive prompt structure template, and generating current retrieval information according to the identified character elements and the coordinate position information of each character element; and inputting the current retrieval information into a pre-training language model, performing text error correction and relation extraction to output an information extraction result, and performing P-tuning training on the basis of the pre-training language model to automatically update the prompt structure template. According to
Bibliography:Application Number: CN202311132052