The invention relates to the technical field of
artificial intelligence, and discloses an interpretable depression detection method and
system, and the method comprises the steps: retrieving a post related to a depressive symptom from a user
social media history; on the basis of the post text corresponding to the symptom problem, a problem
perception text representation is generated through fusion of a Longform
encoder and an attention mechanism, and an optimal reasoning strategy is selected from a predefined reasoning strategy
pool through a
hybrid expert network; based on an
inference strategy of question
perception text representation and selection, selecting a most adaptive large
language model from a predefined large
language model pool through a
hybrid expert network; deducing the severity of each depression symptom of the user according to an
inference strategy and a large
language model, and calculating the overall depression symptom severity of the user; according to the method, the reasoning strategy and the large language model are dynamically selected through the
hybrid expert network, the optimal
processing combination is adaptively matched for different symptom features and post contents, and the limitation of a fixed reasoning mode is overcome.