Research on Intelligent Psychological Consultation Method Based on Dynamic Scale Embedding and Dialogue Analysis

Authors

  • Chenlong Xie School of Computer Science, Chengdu University of Information Technology
  • Ao Feng School of Computer Science, Chengdu University of Information Technology
  • Zhilei Zhang School of Computer Science, Chengdu University of Information Technology

Keywords:

Intelligent Psychological Consultation, Dynamic Scale Embedding, Dialogue Analysis, Retrieval-augmented Generation, Standardized Treatment Plan

Abstract

 Mental health service demands in China keep rising, while traditional psychological counseling is hampered by uneven resource allocation, high costs, delayed responses and inconsistent practitioner expertise. Current intelligent counseling systems mainly adopt rule matching or basic model fine-tuning, leading to rigid dialogue, insufficient professionalism and poor capacity for active assessment and intervention. This paper presents an intelligent psychological counseling approach integrating dynamic scale embedding and dialogue analysis. Its technical framework covers dynamic scale embedding, standardized treatment plan generation, and the collaboration of fine-tuned models and Retrieval-Augmented Generation (RAG). By analyzing dialogue rhythm and semantics, the method embeds psychological scales dynamically via mutual information thresholds to realize unobtrusive assessment. Combined with user portraits and professional knowledge bases, it can automatically produce standardized treatment schemes. The joint use of domain fine-tuning and RAG also improves the empathy, guidance and professionalism of system responses. Experiments show the proposed method surpasses conventional methods in empathy, guidance, professionalism, fluency and reasoning efficiency. It supports low-cost, accessible and standardized intelligent psychological counseling, with great practical value and broad application prospects.

References

Healthy China Initiative Promotion Committee. (2019). Healthy China Initiative (2019–2030) [Government report]. https://www.nhc.gov.cn/wsxf/zcfg/201907/2a771d89e00e4b228028335d4fcf1a7d.shtml

Kermani, A., Perez-Rosas, V., & Metsis, V. (2025, May). A systematic evaluation of LLM strategies for mental health text analysis: Fine-tuning vs. prompt engineering vs. RAG. In Proceedings of the 10th Workshop on Computational Linguistics and Clinical Psychology (CLPsych 2025) (pp. 172-180).

Tao, D., Lee, T., Chui, H., & Luk, S. (2024, April). Modeling intrapersonal and interpersonal influences for automatic estimation of therapist empathy in counseling conversation. In Proceedings of the 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 12692-12696). IEEE.

Hu, J., Wang, A., Xie, Q., Li, Z., Ma, H., & Guo, D. (2026, March). Agentmental: An interactive multi-agent framework for explainable and adaptive mental health assessment. In Proceedings of the AAAI Conference on Artificial Intelligence (pp. 31050-31058).

Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., ... & Hassabis, D. (2015). Human-level control through deep reinforcement learning. Nature, 518(7540), 529–533.

Dutta, A., Mruthyunjaya, S., Saddington, J., & Islam, K. S. (2025, October). Mentalic Net: Development of RAG-based conversational AI and evaluation framework for mental health support. In 2025 IEEE International Symposium on Emerging Metaverse (ISEMV) (pp. 77-84). IEEE.

Du, Z., Qian, Y., Liu, X., Ding, M., Qiu, J., Yang, Z., & Tang, J. (2022, May). GLM: General language model pretraining with autoregressive blank infilling. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 320-335).

Yang, A., Xiao, B., Wang, B., Zhang, B., Bian, C., Yin, C., ... & Wu, Z. (2023). Baichuan 2: Open large-scale language models. arXiv:2309.10305.

Bai, J., Bai, S., Chu, Y., Cui, Z., Dang, K., Deng, X., ... & Zhu, T. (2023). Qwen technical report. arXiv:2309.16609.

Liu, A., Feng, B., Xue, B., Wang, B., Wu, B., Lu, C., ... & Piao, Y. (2024). DeepSeek-V3 technical report. arXiv:2412.19437.

Kafi, M. A. A., Moni, R., & Banshal, S. K. (2026). Reasoning over recall: Evaluating the efficacy of generalist architectures vs. specialized fine-tunes in RAG-based mental health dialogue systems. arXiv:2601.01341.

Kwon, W., Li, Z., Zhuang, S., Sheng, Y., Zheng, L., Yu, C. H., ... & Stoica, I. (2023, October). Efficient memory management for large language model serving with PagedAttention. In Proceedings of the 29th Symposium on Operating Systems Principles (pp. 611-626).

Abd-Alrazaq, A. A., Alajlani, M., Alalwan, A. A., Bewick, B. M., Gardner, P., & Househ, M. (2019). An overview of the features of chatbots in mental health: A scoping review. International Journal of Medical Informatics, 132, 103978.

Torous, J., Bucci, S., Bell, I. H., Kessing, L. V., Faurholt‐Jepsen, M., Whelan, P., ... & Firth, J. (2021). The growing field of digital psychiatry: Current evidence and the future of apps, social media, chatbots, and virtual reality. World Psychiatry, 20(3), 318–335.

Downloads

Published

2026-06-08

How to Cite

Xie, C., Feng, A., & Zhang, Z. (2026). Research on Intelligent Psychological Consultation Method Based on Dynamic Scale Embedding and Dialogue Analysis. International Journal of Advanced AI Applications, 2(7), 16–36. Retrieved from http://www.dawnclarity.press/index.php/ijaaa/article/view/157