人类心理病理机制与AI注意力机制的共性研究：注意力重编程治疗的理论框架与展望
A Study on the Commonalities between Human Psychopathological Mechanisms and AI Attention Mechanisms: Theoretical Framework and Prospects of Attention Reprogramming Therapy
摘要: 目的：通过对比分析人类心理病理机制与AI大模型中的注意力机制，探讨两者的相似性，提出基于“注意力重编程”理论的新型心理治疗框架。方法：采用理论分析、文献综述和跨学科整合的方法，系统梳理人类心理病理中的注意力偏差模式，分析AI注意力机制的基本原理，建立两者的理论联系，构建“注意力重编程治疗”(ART)的理论框架。讨论：理论分析显示，人类情结形成与AI注意力机制具有显著的同构性。心理疾病的形成可以被视为一种“注意力固化”过程，而AI的注意力机制为理解和干预这一过程提供了新的视角。基于这一发现提出的“注意力重编程治疗”(ART)新范式，整合了注意偏差修正训练(ABMT)、正念注意力训练和虚拟现实注意力训练等多种技术。结论：人类心理病理与AI注意力机制存在深刻的共性，注意力重编程治疗为心理治疗提供了新的理论框架和技术路径。本研究为AI在心理健康领域的应用提供了理论基础，为未来实证研究指明了方向。
Abstract: Objective: To compare and analyze the mechanisms of human psychopathology with attention mechanisms in AI large models, explore their similarities, and propose a novel psychotherapy framework based on “attention reprogramming” theory. Methods: Through theoretical analysis, literature review, and interdisciplinary integration, this study systematically examined attention bias patterns in human psychopathology, analyzed the basic principles of AI attention mechanisms, established theoretical connections between the two, and constructed the theoretical framework of “Attention Reprogramming Therapy” (ART). Results: Theoretical analysis revealed significant isomorphism between human complex formation and AI attention mechanisms. The formation of psychological disorders can be viewed as a process of “attention fixation”, while AI attention mechanisms provide new perspectives for understanding and intervening in this process. The proposed new paradigm of “Attention Reprogramming Therapy” (ART) integrates multiple techniques including Attention Bias Modification Training (ABMT), mindfulness attention training, and virtual reality attention training. Conclusions: Human psychopathology and AI attention mechanisms share profound similarities, and attention reprogramming therapy provides a new theoretical framework and technical approach for psychotherapy. This study provides a theoretical foundation for AI applications in mental health and points out directions for future empirical research.
文章引用：豆立宁 (2026). 人类心理病理机制与AI注意力机制的共性研究：注意力重编程治疗的理论框架与展望. 心理学进展, 16(2), 43-56. https://doi.org/10.12677/ap.2026.162060

参考文献

[1] Bahdanau, D., Cho, K., & Bengio, Y. (2014). Neural Machine Translation by Jointly Learning to Align and Translate. arXiv: 1409.0473.
[2] Bar-Haim, Y., Lamy, D., Pergamin, L., Bakermans-Kranenburg, M. J., & van IJzendoorn, M. H. (2007). Threat-Related Attentional Bias in Anxious and Nonanxious Individuals: A Meta-Analytic Study. Psychological Bulletin, 133, 1-24.[CrossRef] [PubMed]
[3] Bolukbasi, T., Chang, K. W., Zou, J. Y., Saligrama, V., & Kalai, A. T. (2016). Man Is to Computer Programmer as Woman Is to Homemaker? Debiasing Word Embeddings. Advances in Neural Information Processing Systems, 29, 4349-4357.
[4] Brewin, C. R. (2006). Understanding Cognitive Behaviour Therapy: A Retrieval Competition Account. Behaviour Research and Therapy, 44, 765-784.[CrossRef] [PubMed]
[5] Brewin, C. R. (2011). The Nature and Significance of Memory Disturbance in Posttraumatic Stress Disorder. Annual Review of Clinical Psychology, 7, 203-227.[CrossRef] [PubMed]
[6] Broadbent, D. E. (1958). Perception and Communication. Pergamon Press.
[7] Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Amodei, D. et al. (2020). Language Models Are Few-Shot Learners. Advances in Neural Information Processing Systems, 33, 1877-1901.
[8] Browning, M., Holmes, E. A., & Harmer, C. J. (2010). The Modification of Attentional Bias to Emotional Information: A Review of the Techniques, Mechanisms, and Relevance to Emotional Disorders. Cognitive, Affective, & Behavioral Neuroscience, 10, 8-20.[CrossRef] [PubMed]
[9] Browning, M., Holmes, E. A., Charles, M., Cowen, P. J., & Harmer, C. J. (2012). Using Attentional Bias Modification as a Cognitive Vaccine against Depression. Biological Psychiatry, 72, 572-579.[CrossRef] [PubMed]
[10] Bylsma, L. M., Morris, B. H., & Rottenberg, J. (2021). A Meta-Analysis of Emotional Reactivity in Major Depressive Disorder. Clinical Psychology Review, 31, 1397-1407.
[11] Cisler, J. M., & Koster, E. H. W. (2010). Mechanisms of Attentional Biases Towards Threat in Anxiety Disorders: An Integrative Review. Clinical Psychology Review, 30, 203-216.[CrossRef] [PubMed]
[12] Clark, K., Khandelwal, U., Levy, O., & Manning, C. D. (2019). What Does BERT Look At? An Analysis of Bert’s Attention. In Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP (pp. 276-286). Association for Computational Linguistics.[CrossRef] 
[13] Cristea, I. A., Kok, R. N., & Cuijpers, P. (2015). Efficacy of Cognitive Bias Modification Interventions in Anxiety and Depression: Meta-Analysis. British Journal of Psychiatry, 206, 7-16.[CrossRef] [PubMed]
[14] Ehlers, A., & Clark, D. M. (2000). A Cognitive Model of Posttraumatic Stress Disorder. Behaviour Research and Therapy, 38, 319-345.[CrossRef] [PubMed]
[15] Gotlib, I. H., & Joormann, J. (2010). Cognition and Depression: Current Status and Future Directions. Annual Review of Clinical Psychology, 6, 285-312.[CrossRef] [PubMed]
[16] Hakamata, Y., Lissek, S., Bar-Haim, Y., Britton, J. C., Fox, N. A., Leibenluft, E. et al. (2010). Attention Bias Modification Treatment: A Meta-Analysis toward the Establishment of Novel Treatment for Anxiety. Biological Psychiatry, 68, 982-990.[CrossRef] [PubMed]
[17] Heeren, A., Mogoaşe, C., Philippot, P., & McNally, R. J. (2015). Attention Bias Modification for Social Anxiety: A Systematic Review and Meta-Analysis. International Journal of Cognitive Therapy, 8, 29-46.
[18] Howard, J., & Ruder, S. (2018). Universal Language Model Fine-Tuning for Text Classification. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 328-339). Association for Computational Linguistics.[CrossRef] 
[19] Jung, C. G. (1934). The Archetypes and the Collective Unconscious. Princeton University Press.
[20] Keng, S., Smoski, M. J., & Robins, C. J. (2011). Effects of Mindfulness on Psychological Health: A Review of Empirical Studies. Clinical Psychology Review, 31, 1041-1056.[CrossRef] [PubMed]
[21] Kircanski, K., Joormann, J., & Gotlib, I. H. (2012). Cognitive Aspects of Depression. WIREs Cognitive Science, 3, 301-313.[CrossRef] [PubMed]
[22] Kuckertz, J. M., Gildebrant, E., Liliequist, B., Karlström, P., Väppling, C., Bodlund, O. et al. (2014). Moderation and Mediation of the Effect of Attention Training in Social Anxiety Disorder. Behaviour Research and Therapy, 53, 30-40.[CrossRef] [PubMed]
[23] MacLeod, C., Rutherford, E., Campbell, L., Ebsworthy, G., & Holker, L. (2002). Selective Attention and Emotional Vulnerability: Assessing the Causal Basis of Their Association through the Experimental Manipulation of Attentional Bias. Journal of Abnormal Psychology, 111, 107-123.[CrossRef] [PubMed]
[24] Maples-Keller, J. L., Bunnell, B. E., Kim, S., & Rothbaum, B. O. (2017). The Use of Virtual Reality Technology in the Treatment of Anxiety and Other Psychiatric Disorders. Harvard Review of Psychiatry, 25, 103-113.[CrossRef] [PubMed]
[25] Mathews, A., & MacLeod, C. (2005). Cognitive Vulnerability to Emotional Disorders. Annual Review of Clinical Psychology, 1, 167-195.[CrossRef] [PubMed]
[26] Michael, T., Ehlers, A., Halligan, S. L., & Clark, D. M. (2005). Unwanted Memories of Assault: What Intrusion Characteristics Are Associated with PTSD? Behaviour Research and Therapy, 43, 613-628.[CrossRef] [PubMed]
[27] Roesler, C. (2019). Evidence for the Effectiveness of Jungian Psychotherapy: A Review of Empirical Studies. Behavioral Sciences, 3, 562-575.
[28] Stein, M. (2019). Jung’s Map of the Soul: An Introduction. Open Court Publishing.
[29] Treisman, A. M., & Gelade, G. (1980). A Feature-Integration Theory of Attention. Cognitive Psychology, 12, 97-136.[CrossRef] [PubMed]
[30] Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Polosukhin, I. et al. (2017). Attention Is All You Need. Advances in Neural Information Processing Systems, 30, 5998-6008.
[31] Voita, E., Talbot, D., Moiseev, F., Sennrich, R., & Titov, I. (2019). Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (pp. 5797-5808). Association for Computational Linguistics.[CrossRef]