Data processing method and device based on large language model

By combining the advantages of large language models and comprehensive scoring models, it solves the scoring problems in enterprise compliance certification and knowledge exams, and achieves scoring accuracy and efficiency.

CN120671806APending Publication Date: 2025-09-19ALIBABA (CHINA) CO LTD
0 Cites 1 Cited by

Patent Information

Application Number
CN202510602281.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-05-09
Publication Date
2025-09-19

AI Technical Summary

Technical Problem

In existing technologies for enterprise compliance certification and knowledge exams, rule-based scoring methods have poor ability to handle complex questions and are costly, while scoring methods based on large language models lack in-depth understanding of specific fields, resulting in inaccurate scoring.

Method used

Combining the large language model and the comprehensive scoring model, by constructing keyword extraction, pseudo-question generation and evaluation generation prompt statements, and utilizing the generalization generation capability of the large language model and the vertical scenario learning capability of the comprehensive scoring model, the text similarity of the answer of the respondent is determined and input into the comprehensive scoring model for scoring.

Benefits of technology

The accuracy of scoring is improved, which not only brings into play the generalization generation ability of the large language model, but also fully utilizes the specific domain understanding ability of the comprehensive scoring model.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The embodiment of the invention discloses a data processing method and device based on a large language model. According to the method, a to-be-scored question group is obtained, the to-be-scored question group comprises questions, answers of answering parties and reference answers, and according to the to-be-scored question group and key words, a prompt template, a false question generation prompt template and an evaluation generation prompt template are extracted, respectively constructing a keyword extraction prompt statement, a pseudo question generation prompt statement and an evaluation generation prompt statement, respectively inputting the constructed statements into a large language model to obtain corresponding keyword groups, question groups and global evaluation, determining text similarity of answers of answering parties and reference answers, and determining the similarity of the answers of the answering parties and the reference answers; and inputting the keyword group, the question group, the global evaluation and the text similarity into a pre-trained comprehensive scoring model to obtain a score corresponding to the answer of the answering party. According to the method, the advantages of the large language model and the comprehensive scoring model are combined, the generalization generation capability of the large language model is exerted, and the vertical domain scene learning capability of the comprehensive scoring model is utilized.
Need to check novelty before this filing date? Find Prior Art