US 12,189,642 B2
Information processing apparatus and prediction method
Kanata Suzuki, Kawasaki (JP); Yoshinobu Iimura, Kawasaki (JP); and Masatoshi Ogawa, Zama (JP)
Assigned to Fujitsu Limited, Kawasaki (JP)
Filed by Fujitsu Limited, Kawasaki (JP)
Filed on Jul. 18, 2023, as Appl. No. 18/223,062.
Claims priority of application No. 2022-150211 (JP), filed on Sep. 21, 2022.
Prior Publication US 2024/0104107 A1, Mar. 28, 2024
Int. Cl. G06F 16/2458 (2019.01)
CPC G06F 16/2477 (2019.01) [G06F 16/2458 (2019.01)] 12 Claims
OG exemplary drawing
 
1. A non-transitory computer-readable recording medium storing a program for causing a computer to execute a process, the process comprising:
generating a prediction model by training a machine learning model for predicting data of a processing target cell using a plurality of pieces of time-series data, each of the plurality of pieces of time-series data includes data at each time in a specific time period;
identifying, among pieces of feature information of a plurality of pieces of time-series data, a plurality of pieces of feature information similar to feature information of processing target time-series data;
obtaining a predicted value distribution of the processing target time-series data based on each of the plurality of pieces of feature information using the prediction model;
combining the predicted value distributions of each of the plurality of pieces of feature information using a mixing coefficient to form a combined distribution;
determining a range of predicted value for the processing target time-series data based on the combined distribution.