The application relates to the technical field of intelligent sports training, and particularly discloses a case reasoning method for personalized sports training driven by cause-effect knowledge and based on man-
machine cooperation, which comprises the following steps: constructing a case
library containing multiple cases and reconstructing cause-effect knowledge at different levels; retrieving a case most similar to a target case from the case
library based on the weight of each description variable; identifying the difference between the training scheme variables of the target case and the retrieved similar case, performing counterfactual intervention and
inference on any training scheme variable of the target case, and screening one or more new cases; when the actual result generated after the execution of the new case does not meet the expectation, executing an attribution process and generating different
processing suggestions according to the attribution type; and storing the new case that does not meet the expectation in the case
library and periodically reconstructing the cause-effect knowledge. The application can deeply integrate cause-effect science and man-
machine interaction to perform personalized training scheme reasoning.