ESTIMATION PROGRAM, ESTIMATION METHOD, INFORMATION PROCESSING DEVICE, RELEARNING PROGRAM, AND RELEARNING METHOD

An information processing device specifies representative points of each of clusters that individually correspond to labels targeted for estimation, which have been generated by clustering in a feature space for a learning data set that contains a plurality of pieces of learning data that has been used for learning of a learning model configured to estimate the labels according to input data. The information processing device sets boundaries of each of the clusters, which are results of the clustering in the feature space for a plurality of pieces of the input data contained in an input data set, under a condition that the number of the clusters and the number of the representative points coincide with each other. The information processing device acquires estimation results for the labels with respect to the plurality of pieces of the input data, based on a correspondence relationship between the clusters of the input data set and the clusters of the learning data set designated based on the boundaries and estimates determination accuracy for the labels determined by using the learning model with respect to the plurality of pieces of the input data, based on the estimation results.