Neural network model training method and electronic equipment

Abstract

The invention provides a neural network model training method and electronic equipment, and the method comprises the steps that the electronic equipment inputs n training samples into a reference neural network model for processing, and obtains a first text recognition result corresponding to each training sample; the electronic equipment inputs the n training samples into an initial neural network model for processing to obtain a second text recognition result corresponding to each training sample; and finally, the electronic equipment adjusts parameters in the initial neural network model according to the first text recognition result, the second text recognition result and a manual annotation result of a first part of training samples in the n training samples to obtain a target neuralnetwork model.

Description

[0001] This application claims the priority of the Chinese patent application with the application number 201811443331.7 and the invention title "An Optical Character Recognition Method" filed with the National Patent Office on November 29, 2018, the entire contents of which are incorporated by reference in this application. technical field [0002] The present application relates to the technical field of machine learning, in particular to a neural network model training method and electronic equipment. Background technique [0003] Deep neural network is a relatively hot research direction in recent years. It simulates the multi-layer computing architecture of the human brain from the perspective of bionics. It is the closest to artificial intelligence. It can better represent the most essential differences in signals. change features. In recent years, in the fields of speech processing, visual processing and image processing, deep learning has achieved good results. Opti...

AI Technical Summary

Problems solved by technology

Limited by the processing power of the artificial intelligence dedicated chip on the terminal side, the neural network model for OCR currently integrated on the server side is not suitable for running directly on the terminal side

For this reason, the terminal side needs to rebuild the neural network model suitable for OCR on the terminal side, but it is difficult to build a neural network model suitable for the terminal side from scratch at present, because the construction of the neural network model needs to rely on a large number of different scenarios. The labeling results of the training samples, and the labeling results of the training samples include manually labeling the text area and text content, so the workload of manual labeling is very large, resulting in very high training costs and low efficiency of the neural network model

Images