Artificial Intelligence-Based Quality Improvement Strategies for Clinical Psychological Counseling Services

Abstract

Clinical psychological counseling suffers from problems such as a shortage of medical personnel and uneven quality, and artificial intelligence technology provides a feasible way to solve these problems. In this paper, a chatbot model for psychological counseling is designed using Seq2seq, and Encoder-Decoder and Attention mechanisms are introduced to improve decoding accuracy. LSTM is used as the basic unit, and the beam search algorithm is added to improve the diversity of replies. The experimental results show that adding LSTM and Beam Search can generate higher-quality and more natural psychological counseling responses, and the loss value of this paper’s model decreases to 1.33 after 10 rounds of training. The total score of the OQ-45.2 questionnaire of the experimental group’s post-test decreased by 13.8 points, and the mean value of symptom distress decreased by 8.26, performing significantly better than that of the control group. The chatbot design in this paper is reasonable and aids in improving the quality of clinical psychological counseling services.

Keywords

• seq2seq
• counseling chatbot
• encoder-decoder
• beam search
• 68t42