平行心理危机干预：方法构建与实现设想

doi:10.3724/SP.J.1042.2026.1058

摘要/Abstract

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。该系统构建了覆盖“监测分析与预测-策略生成与评估-平行执行与优化”的全流程, 旨在为心理危机干预从经验驱动转向计算驱动探索一条可行的技术路径。

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 challenges due to dynamic, complex, and highly personalized nature of mental states. Traditional methods often suffer from delayed monitoring and a lack of closed-loop optimization. While Large Language Models (LLMs) and multi-agent technologies offer new tools, existing research remains fragmented. This paper introduces Parallel Intelligence into mental health and proposes a conceptual framework: Parallel Psychological Crisis Intervention. Based on the ACP approach (Artificial Systems, Computational Experiments, and Parallel Execution), this framework aims to transform intervention from an experience-driven paradigm to a computable, experimental, and iterative one.
The framework begins with the construction of Artificial Psychological Systems (A), which are individual digital twins built from multi-modal data such as physiological signals, behavioral trajectories, and LLM-parsed subjective reports. These artificial systems serve as a virtual laboratory for Computational Experiments (C), allowing practitioners to conduct high-frequency simulations of counterfactual scenarios. This process enables prediction of crisis events and pre-validation of intervention strategies' safety and efficacy, effectively mitigating ethical risks. Finally, Parallel Execution (P) synchronizes the virtual and real worlds, using real-world feedback to continuously calibrate the artificial system. This creates a closed-loop process where the virtual system guides real-world intervention while the real system refines the virtual model.
To demonstrate feasibility, the paper develops PsyRescueGPT, an LLM-driven multi-agent system. The architecture integrates five specialized agents: a Perceptive Agent for data fusion, a Predictive Agent for quantifying crisis probabilities via graph neural networks, a Strategic Agent for generating evidence-based plans, an Experimental Agent for virtual validation of emotional responses, and a Decision Agent as a “Human-in-the-loop” hub for clinician supervision. In a proof-of-concept scenario involving acute suicide risk, PsyRescueGPT executes a cohesive collaborative pipeline. The workflow initiates with digital twin updates and risk identification, followed by the formulation of response plans which are virtually tested through counterfactual simulations. The validated outcomes are then presented to clinicians for final approval, proving that the framework can transform fragmented tools into a seamless, verifiable crisis response workflow.
The theoretical contribution of this work is a systematic modeling language for psychological complexity, while its practical value lies in providing safe, explainable, and supervised AI-led interventions. Future research will focus on the evolution of parallel agents, cross-cultural assessment validation, and rigorous clinical testing of the PsyRescueGPT prototype in diverse scenarios.

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

乔雪, 王静, 宫晓燕. (2026). 平行心理危机干预：方法构建与实现设想. 心理科学进展 , 34(6), 1058-1071.

QIAO Xue, WANG Jing, GONG Xiaoyan. (2026). Parallel psychological crisis intervention: Framework and conceptions. Advances in Psychological Science, 34(6), 1058-1071.

参考文献

[1] 高丽梅, 汪凯, 李丹丹. (2024). 社交机器人在孤独症谱系障碍儿童中的应用. 心理科学进展, 32(5), 834-844.
[2] 郭小丽, 常骏垚, 沙吗阿杰, 杨紫嫣. (2025). 内隐社会认知的干预方法. 心理科学进展, 33(9), 1630-1646.
[3] 王飞跃. (2004a). 人工社会、计算实验、平行系统——关于复杂社会经济系统计算研究的讨论. 复杂系统与复杂性科学, 1(4), 25-35.
[4] 王飞跃. (2004b). 平行系统方法与复杂系统的管理和控制. 控制与决策, 19(5), 485-489, 514.
[5] 王飞跃. (2006). 复杂系统的建模、分析、控制和管理. 复杂系统与复杂性科学, 3(2), 26-34.
[6] 王飞跃. (2021). 平行医学: 从医疗的温度到智慧的医学. 智能科学与技术学报, 3(1), 1-9.
[7] 杨静, 王晓, 王雨桐, 刘忠民, 李小双, 王飞跃. (2023). 平行智能与CPSS: 三十年发展的回顾与展望. 自动化学报, 49(3), 614-634.
[8] 周倩伊, 蔡亚琦, 张亚. (2025). 大语言模型的共情模拟:评估、提升与挑战. 心理科学进展, 33(10), 1783-1793.
[9] Bai, S., Kolter, J. Z., & Koltun, V. (2018). An empirical evaluation of generic convolutional and recurrent networks for sequence modeling.arXiv preprint. Retrieved 2018-04-19, from https://arxiv.org/abs/1803.01271.
[10] Beck A. T., Ward C. H., Mendelson M., Mock J., & Erbaugh J. (1961). An inventory for measuring depression. Archives of General Psychiatry, 4, 561-571.
[11] Zhang Y., Cheng H., He L., Hu B., & Zhang Y. (2024). MAGI: Multi-agent guided interview for psychiatric assessment. arXiv preprint. Retrieved 2025-04-25, from https://arxiv.org/abs/2504.18260.
[12] Bosk, E. A. (2023). Creating a parallel process: A new methodological framework for conducting trauma-informed evaluation and research (TIER) in mental health settings.Evaluation and Program Planning, 97, 102229.
[13] Brickman J., Gupta M., & Oltmanns J. R. (2025). Large language models for psychological assessment: A comprehensive overview. Advances in Methods and Practices in Psychological Science, 8(3), 412-435.
[14] Brown T. B., Mann B., Ryder N., & Subbiah M. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems (NeurIPS),33, 1877-1901.
[15] Bunt H. L., Goddard A., Reader T. W.,& Gillespie, A.(2025). Validating the use of large language models for psychological text classification. Frontiers in Social Psychology, 3, 1460277. https://doi.org/10.3389/frsps.2025.1460277
[16] Caplan, G. (Eds). (1964). Principles of preventive psychiatry. Basic Books.
[17] Carlini, N., & Wagner, D. (2017). Towards evaluating the robustness of neural networks. In 2017 IEEE Symposium on Security and Privacy (SP)(pp. 39-57). IEEE. https://doi.org/10.1109/SP.2017.49
[18] Danieli M., Ciulli T., Mousavi S. M., Silvestri G., Barbato S., Di Natale L., & Riccardi G. (2022). Assessing the impact of conversational artificial intelligence in the treatment of stress and anxiety in aging adults: Randomized controlled trial. JMIR Mental Health, 9(9), e38067.https://doi.org/10.2196/38067
[19] Dwork, C., & Roth, A. (2014). The algorithmic foundations of differential privacy. Foundations and Trends in Theoretical Computer Science,9(3-4), 211-407.
[20] Zhang X., Ren H., Gao L., Shia B. C., Chen M. C., Ye L., Wang R.,& Qin, L.(2023). Identifying the predictors of severe psychological distress by auto-machine learning methods. Informatics in Medicine Unlocked, 39, 101258. https://doi.org/10.1016/j.imu.2023.101258
[21] Ferrario A., Sedlakova J., & Trachsel M. (2024). The role of humanization and robustness of large language models in conversational artificial intelligence for individuals with depression: A critical analysis. JMIR Mental Health, 11, e56569.https://doi.org/10.2196/56569
[22] Freud, S. (1896). Heredity and the aetiology of the neuroses. Revue Neurologique, 4(6), 161-169.
[23] Garriga R., Mas J., Abraha S., Nolan J., Harrison O., Tadros G., Matic A. (2022). Machine learning model to predict mental health crises from electronic health records. Nat Med, 28(6), 1240-1248.
[24] Guo T. C., Chen X. Y., Wang Y. Q., Chang R., Pei S., Chawla N. V.,... Zhang X. (2024. Large language model based multi-agents: A survey of progress and challenges. arXiv preprint. Retrieved 2025-09-18, from 2024). Large language model based multi-agents: A survey of progress and challenges. arXiv preprint. Retrieved 2025-09-18, from http://arxiv.org/abs/2402.01680
[25] Han S., Mao H., & Dally W. J. (2015. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint. Retrieved 2016-01-19, from 2015). Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint. Retrieved 2016-01-19, from http://arxiv.org/abs/1510.00149
[26] Hartzog, W. (2018). Privacy’s blueprint: The battle to control the design of new technologies. Cambridge, MA: Harvard University Press.
[27] Heinz M. V., Mackin D. M., Trudeau B. M., Bhattacharya S., Wang Y.,.. Jacobson N. C. (2025). Randomized trial of a generative AI chatbot for mental health treatment. NEJM AI, 2(4), AIoa2400802.
[28] Hill E. D., Kashyap P., Raffanello E., Wang Y., Moffitt T. E., Caspi A., … Posner J. (2025). Prediction of mental health risk in adolescents. Nature Medicine, 31(6), 1840-1846. https://doi.org/10.1038/s41591-025-03560-7
[29] Hinton G., Vinyals O., & Dean J. (2015). Distilling the knowledge in a neural network. arXiv preprint. https://doi.org/10.48550/arXiv.1503.02531
[30] Hu E. J., Shen Y., Wallis P., Allen-Zhu Z., Li Y., Wang S., Wang L., & Chen W. (2022). LoRA: Low-rank adaptation of large language models. In International Conference on Learning Representations (ICLR 2022). OpenReview. https://openreview.net/forum?id=nZeVKeeFYf9.
[31] Hua Y., Na H., Li Z., Liu F., Fang X., Clifton D., & Torous J. (2025). A scoping review of large language models for generative tasks in mental health care. NPJ Digital Medicin, 8, 230. https://doi.org/10.1038/s41746-025-01611-4
[32] James, R. K., & Gilliland, B. E. (Eds). (2025). Crisis intervention strategies (9th ed.). Cengage Learning.
[33] Kalton A., Falconer E., Docherty J., Alevras D., Brann D., & Johnson K. (2016). Multi-Agent-Based Simulation of a Complex Ecosystem of Mental Health Care. Journal of Medical Systems, 40(2), 39. https://doi.org/10.1007/s10916-015-0374-4
[34] Karkosz S., Szymański R., Sanna K., & Michałowski J. (2024). Effectiveness of a web-based and mobile therapy chatbot on anxiety and depressive symptoms in subclinical young adults: Randomized controlled trial. JMIR Formative Research, 8(1), e47960.https://doi.org/10.2196/47960
[35] Katsoulakis E., Wang Q., Wu H., Shahriyari L., Fletcher R., Liu J.,.. Deng J. (2024). Digital twins for health: A scoping review. NPJ Digital Medicine, 7(1), 77. https://doi.org/10.1038/s41746-024-01073-0
[36] Kjell O. N.E., Kjell, K., & Schwartz, H. A.(2024). Beyond rating scales: With targeted evaluation, large language models are poised for psychological assessment. Psychiatry Research, 333, 115667. https://doi.org/10.1016/j.psychres.2024.115667
[37] Kokkas S., Segkouli S., & Votis K. (2025). Digital twins in older adults’ mental healthcare: A literature review. In I. Maglogiannis, L. Iliadis, & J. Macintyre (Eds.), IFIP International Conference on Artificial Intelligence Applications and Innovations (pp. 185-197). Springer.
[38] Kroenke K., Spitzer R. L., & Williams, J. B. W. (2001). The PHQ-9: Validity of a brief depression severity measure. Journal of General Internal Medicine, 16(9), 606-613.
[39] Lawrence H. R., Schneider R. A., Rubin S. B., Matarić M. J., McDuff D. J., & Bell M. J. (2024). The opportunities and risks of large language models in mental health. JMIR Mental Health, 11, e59479. https://doi.org/10.2196/59479
[40] Lee C., Mohebbi M., O'Callaghan E., & Winsberg M. (2024). Large language models versus expert clinicians in crisis prediction among telemental health patients: Comparative study. JMIR Mental Health, 11(1), e58129. https://doi.org/10.2196/58129
[41] Lindemann, E. (1944). Symptomatology and management of acute grief. American Journal of Psychiatry, 101(2), 141-148.
[42] Lewis P., Perez E., Piktus A., Petroni F., Karpukhin V., Goyal N., … Kiela D. (2020). Retrieval-augmented generation for knowledge-intensive NLP tasks. In H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, & H. Lin (Eds.), Advances in Neural Information Processing Systems (NeurIPS) (Vol. 33, pp. 9459-9474). Curran Associates, Inc.
[43] Mansoor, M. A., & Ansari, K. H. (2024). Early detection of mental health crises through artificial-intelligence-powered social media analysis: A prospective observational study. Journal of Personalized Medicine, 14(9), 958. https://doi.org/10.3390/jpm14090958
[44] Martinez K., Menéndez-Menéndez M. I., & Bustillo A. (2021). Awareness, prevention, detection, and therapy applications for depression and anxiety in serious games for children and adolescents: Systematic review. JMIR Serious Games, 9(4), e30482.https://doi.org/10.2196/30482
[45] McMahan B., Moore E., Ramage D., Hampson S., & y Arcas, B. A. (2017). Communication-efficient learning of deep networks from decentralized data. In A. Singh & J. Zhu (Eds.), Proceedings of the 20th International Conference on Artificial Intelligence and Statistics(AISTATS), 54,
[46] Nahum-Shani I., Smith S. N., Spring B. J., Collins L. M., Witkiewitz K., Tewari A., & Murphy S. A. (2018). Just-in-time adaptive interventions (JITAIs) in mobile health: Key components and design principles for ongoing health behavior support. Annals of Behavioral Medicine, 52(6), 446-452.
[47] Ni, Y., & Jia, F. (2025). A scoping review of AI-driven digital interventions in mental health care: Mapping applications across screening, support, monitoring, prevention, and clinical education. Healthcare, 13(10), 1205. https://doi.org/10.3390/healthcare13101205
[48] Pellert M., Lechner C. M., Wagner C., Rammstedt B., & Strohmaier M. (2024). AI psychometrics: Assessing the psychological profiles of large language models through psychometric inventories. Perspectives on Psychological Science, 19(5), 808-826.
[49] Ravenda F., Bahrainian S. A., Raballo A., Mira A., & Kando N. (2025). Are LLMs effective psychological assessors? Leveraging adaptive RAG for interpretable mental health screening through psychometric practice. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Vol. 1, pp. 8975-8991). Association for Computational Linguistics.
[50] Roy A., Nikolitch K., McGinn R., Jinah S., Klement W., & Kaminsky Z. A. (2020). A machine learning approach predicts future risk to suicidal ideation from social media data. NPJ Digital Medicine, 3(1), 1-12.
[51] Seyedsalehi A., Scola G.,& Fazel, S.(2026). Precision psychiatry: Thinking beyond simple prediction models -Enhancing causal predictions: Commentary. The British Journal of Psychiatry, 2282025.10473
[52] Sezgin, E., & McKay, I. (2024). Behavioral health and generative AI: A perspective on future of therapies and patient care. NPJ Mental Health Research, 3, 25. https://doi.org/10.1038/s44184-024-00056-7
[53] Shen M. D., Chen S. B., & Ding X. D. (2024). The effectiveness of digital twins in promoting precision health across the entire population: A systematic review. NPJ Digital Medicine, 7(1), 145. https://doi.org/10.1038/s41746-024-01146-0
[54] Spitzer M., Dattner I.,& Zilcha-Mano, S.(2023). Digital twins and the future of precision mental health. Frontiers in Psychiatry, 14, 1082598. https://doi.org/10.3389/fpsyt.2023.1082598
[55] Sprint G., Schmitter-Edgecombe M., & Cook D. (2024). Building a human digital twin (hdtwin) using large language models for cognitive diagnosis: Algorithm development and validation. JMIR Formative Research, 8, e63866. https://doi.org/10.2196/63866
[56] Stade E. C., Stirman S. W., Ungar L. H., Boland C. Y., Schwartz H. A., Yaden D. B.,.. Eichstaedt J. A. (2024). Large language models could change the future of behavioral healthcare: A proposal for responsible development and evaluation. NPJ Mental Health Research, 3(1), 12. https://doi.org/10.1038/s44184-024-00056-z
[57] Tan, Y., & Wei, J. Y. (2025). Exploring intervention effects of digital twin city stress visualization systems on mental crisis early warning for occupational populations. Current Opinion in Psychiatry, 38(e-Suppl. 1), e8-e9.
[58] Torous, J., & Blease, C. (2024). Generative artificial intelligence in mental health care: Potential benefits and current challenges. World Psychiatry, 23(1), 1-2.
[59] Torous, J., & Walker, R. (2019). Leveraging digital health and machine learning toward reducing suicide—From panacea to practical tool. JAMA Psychiatry, 76(8), 776-777.
[60] Vaswani A., Shazeer N., Parmar N., Uszkoreit J., Jones L., Gomez A. N., Kaiser L., & Polosukhin I. (2017). Attention is all you need. In I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, & R. Garnett (Eds.), Advances in neural information processing systems,(pp. 5998-6008). Curran Associates, Inc.
[61] Vildjiounaite E., Kallio J., Kantorovitch J., Kinnula H., Ferreira S., Rodrigues M. A., & Rocha N. (2023). Challenges of learning human digital twin: Case study of mental wellbeing: Using sensor data and machine learning to create HDT. In M. Tscheligi, O. Mayora-Ibarra, P. C. Santos, & M. M. da Silva (Eds.), Proceedings of the 16th International Conference on Pervasive Technologies Related to Assistive Environments (pp. 574-583). New York, NY: ACM.
[62] Wang F., Wang X., Li L., & Li L. (2016). Steps toward parallel intelligence.IEEE/CAA Journal of Automatica Sinica, 3(4), 345-348.
[63] Wang, F. Y. (2010). Parallel control and management for intelligent transportation systems: Concepts, architectures, and applications.IEEE Transactions on Intelligent Transportation Systems, 11(3), 630-638.
[64] Washington State Department of Health. (2018). Watch for signs: Stop youth suicide. https://doh.wa.gov/sites/default/files/legacy/Documents/Mtgs/2018/CHWConference/WatchForSigns-YouthSuicide.pdf
[65] Wei J., Wang X., Schuurmans D., Bosma M., Ichter B., Xia F.,.. Zhou D. (2022). Chain-of-thought prompting elicits reasoning in large language models. In S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, & A. Oh (Eds.), Proceedings of the 36th International Conference on Neural Information Processing Systems (pp. 24824-2483). Curran Associates Inc.
[66] World Health Organization. (2023). Suicide worldwide in 2023: Global health estimates. from https://www.who.int/publications/i/item/9789240076846
[67] Xu X. H., Yao B. S., Dong Y. Z., Gabriel S., Yu H., Hendler J.,.. Wang D. (2024). Mental-LLM: Leveraging large language models for mental health prediction via online text data. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 8(1), 1-32.
[68] Yao Y., Lin S., Huang Z., Li S., Guo C., & Wu Y. (2022). Research on the Construction of Psychological Crisis Intervention Strategy Service System. In A. Traina, H. Wang, Y. Zhang, S. Siuly, R. Zhou, & L. Chen (Eds.), Health Information Science(pp. 209-216). Springer Cham.
[69] Zeiler M., Vögl S., Prinz U., Werner N., Wagner G., Karwautz A.,.. Waldherr K. (2025). Game design, effectiveness, and implementation of serious games promoting aspects of mental health literacy among children and adolescents: Systematic review. JMIR Mental Health, 12(1), e67418. https://doi.org/10.2196/67418