山西大学学报（自然科学版）2025，Vol.48Issue(3)：516-526,11.DOI:10.13451/j.sxu.ns.2024158
基于逻辑推理和多任务融合的认知刺激对话生成
Cognitive Stimulation Dialogue Generation Based on Logical Reasoning and Multi-task Integration
摘要
Abstract
In the context of global aging,the health problems of the elderly have gradually become prominent,and cognitive stimula-tion dialogue is an important means to maintain the cognitive health of the elderly.Previous researchers constructed a Chinese cogni-tive stimulation dialogue dataset(CSConv)that includes emotional support,thereby initiating research in the field of Chinese cogni-tive stimulation dialogue.However,the authors did not fully model the logical reasoning relationships within cognitive stimulation dialogues and did not effectively utilize the guiding role of strategy labels during dialogue generation.This study regards cognitive stimulation dialogue generation as a multi-task integration thinking and reasoning process,and models the logical relationship among emotion classification tasks,decision-making tasks and dialogue response generation tasks as a reasoning process to guide the generation of large language models.For decision-making tasks,this paper proposes a decision-making model with a hierarchical encoder structure.The results of the decision-making experiment show that the decision-making model improves the accuracy of the cognitive stimulation therapy principles and emotional support strategies decision-making tasks by 3.96%and 2.1%,respectively.For multi-task logical thinking and reasoning process,this paper proposes a multi-task integration method to combine the models corresponding to the three tasks.The experimental results show that the multi-task integration method has improved BLEU-4 by 7.95%compared with the previous baseline,indicating that the dialogue response ability has been improved,proving the effective-ness and advancement of this method.关键词
认知刺激/情感支持/决策任务/多任务融合方法Key words
cognitively stimulating/emotional support/decision-making tasks/multi-task integration method分类
计算机与自动化引用本文复制引用
蒋玉茹,李梦媛,陶宇阳,区可明,佘泽鹏,施水才..基于逻辑推理和多任务融合的认知刺激对话生成[J].山西大学学报（自然科学版）,2025,48(3):516-526,11.基金项目
北京市自然科学基金(4242019) （4242019）
