The invention provides a
pharmacist clinical ability assessment method and
system based on multi-scene self-adaption, and relates to the technical field of
pharmacist ability assessment, and the method comprises the steps: configuring a standard diagnosis and treatment process, a mapping rule of an operation event and a diagnosis and treatment step, and a reference weight vector of five ability dimensions for various assessment scenes in advance; performing multi-
modal data acquisition on the assessment interaction process of the
pharmacist and the
virtual patient to obtain a dialogue text sequence; performing semantic coding and context modeling on the dialogue text sequence to obtain a global dialogue abstract vector; obtaining a five-dimensional
score vector based on the dialogue text sequence, the diagnosis and treatment step sequence and the pharmaceutical
knowledge graph; adopting an adaptive weight network to generate fusion weight vectors of five capability dimensions; and carrying out weighted aggregation on the five-dimensional
score vector by using the fusion weight vector to obtain a comprehensive
score, and outputting a structured evaluation report. According to the method, the defects of single evaluation scene, shallow scoring dimension and weight logic solidification in the prior art can be overcome.