2026 Vol.9 Jun.N03

• Title: Intelligent Evaluation Method of Teaching Reform Quality of Postgraduates in Obstetrics and Gynecology Based on Macrolanguage Mo
• Name: Zanhui Jia
• Company: The Second Norman Bethune Hospital of Jilin University,Changchun, 130000, China
• Abstract:

  The quality evaluation methods of postgraduate teaching reform in obstetrics and gynecology mostly rely on manual screening of teaching text keywords to give weighted scores. Because it is impossible to quantify the internal relationship between reform measures and postgraduate professional learning behavior, the evaluation quality is not good. In view of this, an intelligent evaluation method of the quality of postgraduate teaching reform in obstetrics and gynecology based on large language model is proposed. Based on the fine-tuned macro-language model of obstetrics and gynecology teaching, the unstructured texts of various types of teaching are analyzed, and the exclusive weighting coefficient is matched in combination with the importance of obstetrics and gynecology teaching, so as to objectively quantify the overall evaluation tendency of the texts on teaching reform. At the same time, the proportion of interactive related sentences is counted and matched with the specialist reinforcement coefficient, and the correlation between reform measures and graduate students' learning behavior is calculated to distinguish paper reform from actual reform. According to the theory of obstetrics and gynecology, clinical practice and assessment mechanism, the reform plates are divided, and at the same time, the feedback subjects such as graduate students and teachers are distinguished from the reform implementation cycle, and the differentiated zoning weights are automatically generated. Fusion of all text two-dimensional measurement data by coupling summation operation. Based on the big language model, the specialty adaptation correction coefficient is deduced according to the training standard of obstetrics and gynecology graduate students, and the defect correction compensation term is generated in combination with the global negative feedback distribution, so as to solve the hierarchical quality judgment index. In the experiment, the evaluation quality of the proposed method is tested. The final test results show that the average difference recognition of the improved algorithm is 0,763, which has an ideal evaluation effect.

  
  

• Keyword: large language model; Obstetrics and gynecology; Graduate students; Teaching reform; Quality evaluation;
• DOI: 10.12250/jpciams2026090603
• Citation form: [J]. Computer Informatization and Mechanical System,2026,Vol.9,pp.

[1] Xujie L I , Yuchen G U ,  Yao C .Design and implementation of an online programming experiment platform integrated with AI large language models[J].Experimental Technology and Management, 2024, 41(8):215-221.

[2] Liao J , Yu-Li H U , Zhang Q , et al.Research on the CST2 Differentiated Lesson Evaluation Model and Its Application Based on Multimodal Large Models[J].Modern Educational Technology, 2025, 35(5):52-61.

[3] Zeng J , Meng F , Yin Y ,et al.Teaching Large Language Models to Translate with Comparison[J].Proceedings of the AAAI Conference on Artificial Intelligence, 2024, 38(17):19488-19496.

[4] Xiao Y H , Zou Y M , Feng W Q , et al.Research on the Evaluation Analysis and Enhancement Path of Foreign Language Teachers' Digital Literacy Competence in Colleges and Universities[J ].Modern Educational Technology, 2024, 34(10):83-91.

[5] Shrestha N .An Evaluation of Master of Education in English Language Teaching (M.Ed. in ELT) of Kathmandu University, School of Education Using CIPP Model[J].ELE Praxis, 2024, 1(1):52-58.

[6] Chen S .A Framework of Multilingual Conversion Errors: A Crosslinguistic Mediation Model in Teaching Chinese as a Second Language:[J].SAGE Open, 2025, 15(4):530-541.

[7] Chen Y .Design of English Teaching Quality Evaluation System Based on Deep Learning and Data Mining[J] .2024 IEEE 2nd International Conference on Image Processing and Computer Applications (ICIPCA), 2024, 2021:1833-1836.

[8] Lee S , Jeon J , Mckinley J ,et al.Generative AI and English language teaching: A global Englishes perspective[J].Annual Review of Applied Linguistics, 2025, 45(000):85-108.

[9] Liu M , Yang M , Zhong-Ming W U ,et al.Development, Application Status and Future Prospect of Large Language Model Agents for Education[J].Modern Educational Technology, 2024, 34(11):5-14.D

[10] Zhang L , Rentao G U , Wang Q .A study on the application of large language models in language experiment teaching[J].Experimental Technology and Management, 2025, 42(10):201-209.

[11] Guthrie E , Levy D ,  Carmen G D .The Operating and Anesthetic Reference Assistant (OARA): A fine-tuned large language model for resident teaching[J].The American Journal of Surgery, 2024, 234:28-34.

[12] Wei S P , Zhang Y , Ran R .Chinese Composition Evaluation Ability Test of Domestic Large Language Model[J].Modern Educational Technology, 2025, 35(3):24-33.

[13] Yang H .Python Language Teaching Evaluation System Based on LLM large model[J].International Journal of Computer Science and Information Technology, 2024, 4(1):93-100.

[14] Zhang H , Zheng C , Zhao Y ,et al.Large Language Model Assisting Teaching Evaluation in Online Learning Scenarios[J].Modern Educational Technology, 2024, 34(11):15-26.

[15] Jaashan H M S .Large Language Model (LLM-ChatGPT) and Learner Autonomy: Teaching Present Simple Tense as a Model[J].Open Journal of Applied Sciences, 2025, 15(2):450-462