ELECTRONIC DEVICE FOR PROVIDING A FEEDBACK FOR A SPECIVIC MOTION USING A MACHINE LEARNING MODEL A AND MACHINE LEARNING MODEL AND METHOD FOR OPERATING THEREOF

摘要

According to an embodiment of the present application, a method of operating an electronic device, comprising: information on a plurality of skeletons associated with a specific movement of a professional and/or a professional player associated with a specific event accumulated in the server from a server, and associated with the specific movement. Receiving a program including a machine learning model generated by performing machine learning using information on a plurality of angular velocities and/or a plurality of evaluation information related to the specific operation as training data; The evaluation information includes information on evaluation levels for each of a plurality of characteristics associated with the specific motion, and the machine learning model responds to input of at least one of information on a first skeleton or information on a first angular velocity. As, it is set to output first evaluation levels for the plurality of characteristics associated with the specific operation, execute the program, and based on the execution of the program, the specific operation of the user of the electronic device from the swing exerciser Receiving information on a second angular velocity for the second angular velocity; Based on the execution of the program, photographing of the specific motion of the user is performed, and information on the second joint during the specific motion of the user is obtained based on a plurality of images acquired based on the execution of the photographing. Obtaining; Displaying a 3D graphic user interface (GUI) including a 3D animation object based on information on the second angular velocity and/or information on the second joint; And in response to inputting information on the second angular velocity and/or information on the second joint into the machine learning model, the plurality of characteristics associated with the specific motion output from the machine learning model. Displaying information on the second evaluation levels on the 3D graphical user interface; comprising, an operation method is provided. Other various embodiments are possible.