Intelligent paper marking system based on large language model

The intelligent marking system based on a large language model solves the problems of low efficiency and insufficient accuracy in traditional marking, and achieves efficient and accurate scoring and personalized feedback for multi-disciplinary test papers, adapting to diverse educational needs.

CN120808370APending Publication Date: 2025-10-17FUZHOU UNIV
View PDF 0 Cites 4 Cited by

Patent Information

Application Number
CN202510919509.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-07-04
Publication Date
2025-10-17

AI Technical Summary

Technical Problem

Traditional manual marking is inefficient and susceptible to subjective factors. Existing intelligent marking systems are inadequate in character recognition and scoring accuracy, making it difficult to adapt to diverse examination needs and lacking interpretable feedback.

Method used

An intelligent marking system based on a large language model is adopted, which includes a candidate's test paper character recognition module, a subject knowledge base, a subject knowledge retrieval module, a scoring template generator module, a large language model scoring module, and a comment correction module. Through multi-stage optimization design, efficient and accurate evaluation is achieved.

Benefits of technology

It significantly improves the integrity and accuracy of character recognition, supports multi-disciplinary test paper scoring, provides personalized learning guidance, adapts to different teaching syllabi and scoring standards, and improves assessment efficiency and interpretability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120808370A_ABST
    Figure CN120808370A_ABST
Patent Text Reader

Abstract

The invention provides an intelligent paper marking system based on a large language model. The intelligent paper marking system comprises an examinee test paper character recognition module used for carrying out image processing and content recognition on scanned or shot student answer sheets or answer sheets; the subject knowledge base is used for performing systematic arrangement and representation modeling on multi-subject teaching contents; the subject knowledge retrieval module is used for performing semantic analysis and matching on test paper questions and examinee answering contents to obtain subject knowledge related to the test questions and a scoring basis; a scoring template generator module; a large language model scoring module; and the comment correction module is used for optimizing and adjusting the preliminary comments generated by the large language model and outputting final comments with more pertinence and teaching guidance significance. The technical scheme can be widely applied to automatic evaluation scenes of subjective questions in the education field.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Cited By

  • Mushroom growth light supplement control method and system based on multispectral LED light source

    CN120980737A

  • Intelligent teaching assisting system, learning path optimization method, equipment and medium

    CN121190278A

  • Class learning condition analysis system and method based on AI large model

    CN121304411A

  • Large language model marking method, system and equipment based on iterative knowledge enhancement and medium

    CN121328688A