公开(公告)号：US20200210895A1

公开(公告)日：2020-07-02

申请号：US16694921

申请日：2019-11-25

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Youngwoong HAN ,  Hwin-Dol PARK ,  Jae-Hun CHOI

IPC: G06N20/00 ,  G16H50/20

Abstract: The time series data processing device according to an embodiment of the inventive concept includes a preprocessor, a learner, and a predictor. The preprocessor preprocesses time series data to generate interval data, interpolation data, and masking data. The learner generates a weight value group of a prediction model that generates a feature weight value and a time series weight value, based on the interval data, the interpolation data, and the masking data. The feature weight value depends on a time and a feature of the time series data and the time series weight value depends on a time flow of the time series data. The predictor generates a feature weight value and a time series weight value, based on the weight value group, and generates a prediction result, based on the feature weight value and time series weight value.