Abstract: A device and method to estimate a word sense with high accuracy by unsupervised learning. A word sense estimation device executes a plurality of number of times a probability calculation of calculating an evaluation value for each word of a case where each concept extracted as a word sense candidate is determined as a word sense, based on a proximity between a context feature of a selected word and a context feature of another word, a proximity between a selected concept and a word sense of this another word, and a probability that the selected word takes a selected word sense, and of re-calculating the probability based on the evaluation value calculated, and estimates a concept with a higher probability calculated of said each word, to be a word sense of the word.

Abstract: The present invention aims to facilitate integration of databases by classifying a plurality of tables in databases into a group of similar tables. A table classification device 1 includes a semantic classifying unit 20 carrying out classification with considering meanings of columns which form a database and a statistical classifying unit 30 carrying out classification based on statistical information of the columns. The tables are classified hierarchically by combining a classification method of the semantic classifying unit 20 and a classification method of the statistical classifying unit 30.

Abstract: The present invention aims to facilitate integration of databases by classifying a plurality of tables in databases into a group of similar tables. A table classification device 1 includes a semantic classifying unit 20 carrying out classification with considering meanings of columns which form a database and a statistical classifying unit 30 carrying out classification based on statistical information of the columns. The tables are classified hierarchically by combining a classification method of the semantic classifying unit 20 and a classification method of the statistical classifying unit 30.

Abstract: A time series data dimensional compression apparatus performing dimensional compression for improving the efficiency of searching for time series data without losing the features of data. The compression is made to a determined dimension so that a larger volume of information may be extracted therein. A time series subsequence generating section (112) generates time series subsequences of a specified segment width into which a plurality of pieces of time series data generated at a time series data generating section (110) are divided. A singular value decomposition processing section (113) performs singular value decomposition on all of the time series subsequences. A dimensional compression time series data generating section (114) generates dimensional compression time series data by using high-order elements of the singular value decomposition as a representative value of the time series subsequence.

Abstract: A time series data dimensional compression apparatus performing dimensional compression for improving the efficiency of searching for time series data without losing the features of data. The compression is made to a determined dimension so that a larger volume of information may be extracted therein. A time series subsequence generating section (112) generates time series subsequences of a specified segment width into which a plurality of pieces of time series data generated at a time series data generating section (110) are divided. A singular value decomposition processing section (113) performs singular value decomposition on all of the time series subsequences. A dimensional compression time series data generating section (114) generates dimensional compression time series data by using high-order elements of the singular value decomposition as a representative value of the time series subsequence.