ISSN 1671-3710
CN 11-4766/R
主办：中国科学院心理研究所
出版：科学出版社

• •    

平行心理危机干预：方法构建与实现设想

乔雪, 王静, 宫晓燕   

  1. 北京中医药大学护理学院, 北京 100190 中国
    中国科学院自动化研究所多模态人工智能系统全国重点实验室, 北京 100190 中国
    澳门科技大学系统工程所, 澳门特别行政区 999078 中国
  • 收稿日期:2025-09-24 修回日期:2026-01-23 接受日期:2026-01-26
  • 基金资助:
    跨模态胰腺癌铂敏感智能热力图生成模型及多中心联邦优化研究(82372051); 基于联邦学习的多发性骨髓瘤全身MR病灶自动分割模型的构建和性能评估(L222099); 基于术前评估多模态数据构建嗜铬细胞瘤/副神经节瘤术中血流动力学波动风险分级预测模型(2024-2-4015); 基于大数据和人工智能的老年跌倒风险评估、预防与处置一体化系统的研发及验证(2024YFHZ0011)

Parallel Psychological Crisis Intervention: Framework and Conceptions

  1. School of Nursing, Beijing University of Chinese Medicine 100190, China
    State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences 100190, China
    Department of Engineering Science, Faculty of Innovation Engineering, Macau University of Science and Technology 999078, China
  • Received:2025-09-24 Revised:2026-01-23 Accepted:2026-01-26
  • Supported by:
    Construction and muti-center federal optimization of the synthetic model of cross-modal intelligent heat map for platinum sensitivity in pancreatic cancer(82372051); Construction and performance evaluation of a federated learning based whole-body MR lesion segmentation model for multiple myeloma(L222099); Development of a Preoperative Multimodal Data-Based Predictive Model for Risk Stratification of Intraoperative Hemodynamic Fluctuations in Pheochromocytoma and Paraganglioma (PPGL) Surgery(2024-2-4015); Development and Validation of an Integrated System for Fall Risk Assessment, Prevention, and Management in Older Adults Based on Big Data and Artificial Intelligence(2024YFHZ0011)

PDF (PC)

0

摘要： 摘 要 心理危机干预面临动态监测、精准预测与策略优化的方法挑战，传统方法难以应对心理状态的复杂性和个性化需求。本文探讨把平行智能理论引入心理危机干预，提出一个平行心理危机干预框架的概念。该框架基于ACP方法(Artificial society, Computational experiments, Parallel execution，人工系统+计算实验+平行执行)，试图通过构建人工心理系统实现状态建模，通过计算实验实现心理状态推演与干预策略评估，通过平行执行实现虚实交互的策略优化，旨在为实现可计算、可实验、可迭代的心理危机干预方法提供初步框架。作为该框架的概念验证原型，本文设计了大语言模型驱动的多智能体系统：PsyRescueGPT，试图通过构建覆盖从监测与分析预测、策略生成与评估、平行执行与优化全流程，以期为心理危机干预从经验驱动向计算驱动提供可能的技术路径。

关键词: 心理危机干预, 平行智能, ACP, 大语言模型, 多智能体系统, 个性化干预

Abstract: Psychological crisis intervention faces significant methodological challenges in dynamic monitoring, precise prediction, and strategy optimization. Traditional methods often struggle with the inherent complexity and personalized needs of psychological states. This paper explores the introduction of Parallel Intelligence theory into psychological crisis intervention and proposes a conceptual framework for Parallel Psychological Crisis Intervention. Based on the ACP approach (Artificial Systems, Computational Experiments, and Parallel Execution), this framework aims to achieve state modeling by constructing artificial psychological systems, derive psychological states and evaluate intervention strategies through computational experiments, and optimize strategies via virtual-real interaction through parallel execution. It is designed to provide a preliminary framework for computable, experimental, and iterative psychological crisis intervention. As a proof-of-concept prototype, this paper develops PsyRescueGPT, a Large Language Model-driven multi-agent system. This system covers the entire process from monitoring, analysis, and prediction to strategy generation, evaluation, and parallel execution/optimization, providing a potential technical path for transitioning psychological crisis intervention from experience-driven to computation-driven paradigms.

Key words: psychological crisis intervention, parallel intelligence, ACP, Large Language Models, multi-agent systems, personalized intervention