郑州大学学报（理学版）2026，Vol.58Issue(5)：62-68,7.DOI:10.13705/j.issn.1671-6841.2025056
基于思维链与时空类案辅助的刑期预测方法
Prison Term Prediction Based on Chain-of-thought and Spatio-temporal Case Assistance
摘要
Abstract
In the field of legal artificial intelligence,the task of prison term prediction faced the dual challenges of slow improvement in accuracy and insufficient model interpretability.To address these is-sues,a prison term prediction method integrating chain-of-thought reasoning and case analysis was pro-posed,aimed at simulating the sentencing mindset that combined qualitative and quantitative approach in judicial practice.A three-stage reasoning framework was constructed in the proposed method.In the first stage,the sentencing starting range was determined based on the legal provisions.In the second stage,the baseline sentencing range was derived by combining the characteristics of criminal facts.In the third stage,case comparison in the temporal-spatial dimension was introduced to refine the results.One-shot chain-of-thought reasoning mechanisms were incorporated in each stage to explicitly extract and compare key features of the legal provisions and cases,thus achieving transparency and interpretability of the rea-soning process.Experimental results demonstrated a significant performance improvement of the proposed method on publicly available legal datasets,validating its effectiveness and practicability.关键词
刑期预测/类案分析/大语言模型/思维链推理/非参数学习Key words
prison term prediction/case analysis/large language model/chain-of-thought reasoning/non-parametric learning分类
信息技术与安全科学引用本文复制引用
田合海,余帅,秦永彬,黄瑞章,陈艳平,韩德毅..基于思维链与时空类案辅助的刑期预测方法[J].郑州大学学报（理学版）,2026,58(5):62-68,7.基金项目
国家重点研发计划项目(2023YFC3304500) （2023YFC3304500）
贵州省科学技术基金重点资助项目(黔科合重大专项[2024]003) （黔科合重大专项[2024]003）
贵州省科技支撑计划资助项目(黔科合支撑[2023]一般448) （黔科合支撑[2023]一般448）
