DEVICE, PROGRAM AND METHOD FOR LABELING, AND RECORDING MEDIUM RECORDING LABELING PROGRAM

摘要

PROBLEM TO BE SOLVED: To generate a labeling model for achieving pre-learning for labeling and highly precise labeling in a short calculation time. SOLUTION: In an automatic multi-labeling device 1, a conditional probability model generation section 4 generates a conditional probability model 53 serving as a labeling model, by performing weighted integration of a classification model 51 and a bias correction model 52 on the basis of a parameter of the classification model 51, a parameter of the bias correction model 52 and an integration parameter. COPYRIGHT: (C)2010,JPO&INPIT