The invention relates to the technical field of
artificial intelligence, in particular to a real world model training method and
system based on a local physical environment, and the method comprises the steps: providing a common rule of a second
modal feature of a target physical place in a historical time period through a local rule
knowledge base; classifying second
modal features of the target physical place in a target time period, adding category labels to the second
modal features, adding the second modal features into a
training set of a cloud world model, and performing model
distillation on the cloud world model of the cloud together with a local rule
knowledge base, the first modal features and the second modal features; the personalized features corresponding to the target physical place are determined, so that the real world model can dynamically adapt to the personalized rules and dynamic changes of the target physical place, and the characterization degree and adaptability of the real world model to the target physical place are improved.