发明名称 Method and apparatus for mining temporal pattern
摘要 An apparatus and a method for mining temporal pattern are provided. A method for mining temporal pattern includes generating a data pattern group comprising data patterns from sequential data, generating a candidate pattern group comprising candidate patterns from the data pattern group, calculating a support value for a candidate pattern in a candidate pattern group based on a discrepancy value of the candidate pattern, and determining whether the candidate pattern satisfies a predetermined pattern requirement, based on the calculated support value.
申请公布号 US9465912(B2) 申请公布日期 2016.10.11
申请号 US201414267351 申请日期 2014.05.01
申请人 Samsung Electronics Co., Ltd. 发明人 Park Hyoung-Min;Kang Hyo-A;Lee Ki-Yong
分类号 G06F7/00;G06F17/30;G06F19/24;G06F19/00;G06K9/68 主分类号 G06F7/00
代理机构 NSIP Law 代理人 NSIP Law
主权项 1. A method for mining temporal pattern based on an interest pattern model, the method comprising: generating by a processing device a data pattern group comprising data patterns with a same length; generating a candidate pattern group comprising candidate patterns based on the data pattern group, each candidate pattern of the candidate pattern group having discrepancy values equal to or smaller than a maximum discrepancy value of the interest pattern model, with respect to each data pattern in the data pattern group; calculating a support value for each candidate pattern in the candidate pattern group by applying a weight varying based on the discrepancy value with respect to each data pattern of the data pattern group; determining whether each candidate pattern satisfies a predetermined pattern requirement, based on the calculated support value for a corresponding candidate pattern, in response to a determination that a length of a candidate pattern is not identical to an intended pattern length of the interest pattern model, eliminating a data pattern, whose discrepancy values with respect to each of the other candidate patterns in the candidate pattern group are all greater than the maximum discrepancy value, from the data pattern group; and generating a new data pattern group by combining remaining data patterns, after the elimination, with a pattern unit based on the data suffix tree.
地址 Suwon-si KR