Answer information recognition method and device, electronic equipment and storage medium

By extracting visual feature information through an end-to-end answer recognition model and a Conv2former model, and combining it with reference answer information, the problem of recognizing handwritten answers that are not written in the designated area is solved, achieving efficient and accurate answer information recognition.

CN122290150APending Publication Date: 2026-06-26IFLYTEK CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
IFLYTEK CO LTD
Filing Date
2026-03-25
Publication Date
2026-06-26

AI Technical Summary

Technical Problem

In existing technologies, when students write their answers outside the designated answer area, it can easily lead to problems such as the answer information not being recognized or a high recognition error rate.

Method used

An end-to-end answer recognition model is adopted, which uses the Conv2former model with attention mechanism to extract visual feature information of the image to be recognized, and combines it with the reference answer information for recognition. The feature information is fused through a multi-head cross-attention mechanism to achieve accurate recognition of handwritten answer information.

Benefits of technology

It can accurately identify handwritten answers without specifying the answer area, improving recognition efficiency, avoiding recognition failures caused by changes in the answerer's writing position, and enhancing the accuracy and robustness of recognition.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122290150A_ABST
    Figure CN122290150A_ABST
Patent Text Reader

Abstract

This application relates to a method, apparatus, electronic device, and storage medium for recognizing answer information, applied in the field of computer technology. The method includes: acquiring an image to be recognized, the image including a question; acquiring reference answer information corresponding to the question; extracting visual feature information from the image to be recognized based on an end-to-end answer recognition model; recognizing the image to be recognized based on the reference answer information and the visual feature information to obtain answer information corresponding to the question; the visual feature information is used to indicate the spatial positional relationship and contextual information between pixels in the image to be recognized; the end-to-end answer recognition model includes a Conv2former model with an attention mechanism; and the answer information includes handwritten answer information.
Need to check novelty before this filing date? Find Prior Art