Error collection method, device and equipment based on deep learning

Abstract

The invention provides an error collection method, device and equipment based on deep learning. The method comprises: acquiring corrected homework or test paper images containing multiple questions; carrying out topic segmentation on the obtained image by adopting a pre-trained topic coordinate-based recognition model to obtain a coordinate region corresponding to each topic; and identifying the correction trace in the coordinate area corresponding to each question according to a pre-trained detection model based on the correction trace so as to obtain the right and wrong judgment of the question.

Description

technical field [0001] The present invention relates to the field of machine learning, and in particular to a method, device and equipment for collecting wrong questions based on deep learning. Background technique [0002] It is inevitable and normal for students to make mistakes in the learning process. The wrong question itself reflects the problems and deficiencies in a student's understanding or application of knowledge. Therefore, only by finding out the loopholes in knowledge points and weaknesses in personal habits and thinking in the test-taking through wrong questions, and correcting them, can the wrong questions done be transformed into the most valuable learning resources. [0003] Now students have a large amount of exercises and a considerable amount of wrong questions. However, the efficiency of collecting wrong questions by traditional handwriting or copying and cutting and pasting is too low. Such complicated mechanical work is not easy to maintain. The so...

Images