Information identification method and device based on graph convolutional neural network, and storage medium

Abstract

The invention relates to an information identification method and device based on a graph convolutional neural network and a storage medium, and belongs to the technical field of computers, and the method comprises the steps of obtaining semantic features of text blocks in a target image, and visual features between different text blocks; inputting the feature information of each text block into a first graph convolutional neural network to obtain a text block type and an implicit vector, wherein the feature information comprises semantic features of the text blocks, semantic features of the associated text blocks and visual features between the text blocks and the associated text blocks; inputting the implicit vector of the text block, the text block type and the character feature information of the character into a preset character model to obtain a character type of the character; inputting the character information of each character into a second graph convolutional neural network to obtain an edge attribute; identifying entity blocks based on edge attributes. The problem that the accuracy is not high when semantic features are used for information recognition can be solved. Type reasoning can be performed in combination with semantic and spatial features, and the accuracy of information identification is improved.

Description

technical field [0001] The present application relates to an information recognition method, device and storage medium based on a graph convolutional neural network, which belongs to the field of computer technology. Background technique [0002] Information recognition (or named entity recognition) is a fundamental problem in the field of natural language processing. Simply put, named entity recognition is to identify and classify entities of interest contained in a text sequence, for example, to extract key information from documents such as bills and logistics orders. [0003] At present, information recognition methods include: named entity recognition based on a linear chain language model (such as: Bidirectional Encoder Representations from Transformers, BERT). [0004] However, since the text to be recognized may have semantic particularity, irregular typesetting layout, and irregular word segmentation granularity, etc., the accuracy of information recognition may no...

AI Technical Summary

Problems solved by technology

[0005] This application provides an information recognition method, device and storage medium based on a graph convolutional neural network, which can solve the problem of low recognition accuracy when only using semantic features for information recognition

Images