一种基于大模型增强的半结构化精神障碍访谈方法
By introducing clinical guidelines and large language models to generate standardized questions, and combining them with a multi-agent collaborative framework, the problems of insufficient diagnostic interpretability and incomplete interview assessment in the diagnosis of mental disorders are solved, achieving efficient and accurate diagnosis of mental disorders and improving doctor-patient relationships.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- EAST CHINA UNIV OF SCI & TECH
- Filing Date
- 2025-04-15
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies lack the structured incorporation of clinical medical knowledge in the diagnosis of mental disorders, resulting in insufficient interpretability of diagnoses, unadaptable question generation, and an imperfect interview assessment system, which affects the accuracy and efficiency of diagnosis.
We construct a semi-structured interview method for mental disorders based on large model enhancement. By introducing clinical guidelines and structured medical knowledge, we combine a large language model to generate standardized questions, and use a multi-agent collaborative framework to achieve dynamic follow-up questioning and decision reasoning, and construct an interview content evaluation mechanism.
It improves the accuracy and efficiency of mental disorder diagnosis, enhances patient cooperation, ensures the safety and ethical compliance of interview content, and promotes doctor-patient communication and decision-making sharing.
Smart Images
Figure CN120412970B_ABST