Answer recognition method and system for textual test questions

Abstract

The invention discloses an answer recognition method and system for literal test questions. The method includes: obtaining an answer image of a literal test question; obtaining one or more answer character strings to be recognized from the answer image; The model performs handwriting recognition on the answer string to be recognized to obtain a first recognition result; obtains the answer information of the literal test question; constructs an adaptive acoustic model according to the first recognition result and the answer information of the literal test question; Using the adaptive acoustic model to perform handwriting recognition on the answer character string to be recognized to obtain a final recognition result. The invention can effectively improve the recognition accuracy of literal objective questions, and further improve the efficiency and accuracy of examination papers.

Description

technical field [0001] The invention relates to the technical field of information processing, in particular to an answer recognition method and system for literal test questions. Background technique [0002] With the continuous advancement of computer technology and educational informatization, computer and artificial intelligence technology has been gradually applied to daily educational and teaching activities, and has been applied in practical application scenarios such as teaching assistance and teaching evaluation. Existing basic education in China and the main examination forms of students' learning status are still various types of examinations or tests. In this situation, teachers are under great pressure to correct homework and test papers. In response to this phenomenon, various automatic marking systems have been gradually promoted and adopted in large and medium-sized or high-importance examinations or tests. Such systems can reduce the workload of teachers mar...

AI Technical Summary

Problems solved by technology

[0003] However, in the existing automatic marking system, most of the marking completed by the computer is marking of objective questions (such as multiple choice questions), while marking of textual test questions (such as filling in the blanks and short answer questions) is mostly done by computers. still mainly conducted intensively by teachers or trained professionals

In the traditional automatic marking system, because the accuracy of computer marking and recognition of textual test questions has not yet reached the expected value of widespread use, manual marking is still performed so far, resulting in low marking efficiency, high consumption of human resources, and subjective factors due to marking people. Problems such as marking deviations caused by

Images