公开(公告)号：US20210138301A1

公开(公告)日：2021-05-13

申请号：US16705185

申请日：2019-12-05

Applicant: Institute For Information Industry

Inventor： Chia-Yu LU ,  Shang-Ming JEN

IPC: A63B24/00 ,  G06K9/00 ,  G06N20/00 ,  G09B19/00

Abstract: An exercise assisting device and exercise assisting method are provided. The device performs the following operations: transmitting a first control signal, the first control signal is related to a motion demonstration video corresponding to an exercise course data; receiving a video stream of a user; analyzing the video stream to generate a motion recognition result corresponding to the exercise course data of the user, and determining whether a motion target value is achieved according to the motion recognition result and the exercise course data; and when the motion target value is not achieved, the motion recognition result and the motion target value are input into an expert suggestion model to generate a follow-up motion suggestion and to determine a follow-up motion demonstration video corresponding to the follow-up motion suggestion.

公开(公告)号：US20190179906A1

公开(公告)日：2019-06-13

申请号：US15839787

申请日：2017-12-12

Applicant: Institute For Information Industry

Inventor： Chia-Min LAI ,  Chia-Yu LU

IPC: G06F17/28 ,  G06F21/56 ,  G06F17/27 ,  G06K9/62 ,  G06K9/72

Abstract: A behavior inference model building apparatus and a behavior inference model building method thereof are provided. The behavior inference model building apparatus converts a plurality of program operation sequences of a plurality of program operation sequence data into a plurality of word vectors through a word embedding model, and inputs the first M word vectors of the word vectors, corresponding to each program operation sequence data, into a generative adversarial network (GAN) model to train and optimize the GAN model. The behavior inference model building apparatus integrates the word embedding model and the generator of the optimized GAN model to build a behavior inference model.