DEVICE STATE PREDICTION METHOD, DEVICE STATE PREDICTION SERVER AND DEVICE STATE PREDICTION SYSTEM

• Main Authors: FUJIBAYASHI ICHIRO, MURATA YUKIO, OBARA KIYOHIRO
• Format: Patent
• Language: English; Japanese
• Published: 04.01.2023
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

To predict occurrence of a predetermined event on the basis of an actual result of a past use status of a device.SOLUTION: A device state prediction method executed by a device state prediction system having a processor and a storage device, wherein the storage device holds sensor data measured by a sensor installed in a plurality of refrigerators, and the device state prediction method includes a procedure of imparting a feature amount to sensor data measured in a first period, a procedure of specifying a refrigerator whose temperature in a second period later than the first period satisfies a predetermined condition on the basis of sensor data measured in the second period, a procedure of learning a model of estimating a refrigerator whose temperature in the second period satisfies the predetermined condition on the basis of the feature amount of the sensor data measured in the first period, and a fourth procedure of estimating a refrigerator whose temperature in a fourth period later than a third period satisfies a predetermined condition by inputting the feature amount of the sensor data measured in the third period to the model.SELECTED DRAWING: Figure 1 【課題】機器の過去の使用状況の実績に基づいて、所定の事象が発生することを予測する。【解決手段】プロセッサと、記憶装置と、を有する機器状態予測システムが実行する機器状態予測方法であって、記憶装置は、複数の冷蔵庫に設置されたセンサによって計測されたセンサデータを保持し、機器状態予測方法は、第１の時期に計測されたセンサデータに特徴量を付与する手順と、第１の時期より後の第２の時期に計測されたセンサデータに基づいて、第２の時期における庫内の温度が所定の条件を満たす冷蔵庫を特定する手順と、第１の時期に計測されたセンサデータの特徴量に基づいて第２の時期における庫内の温度が所定の条件を満たす冷蔵庫を推定するモデルを学習する手順と、第３の時期に計測されたセンサデータの特徴量をモデルに入力することによって、第３の時期より後の第４の時期に庫内の温度が所定の条件を満たす冷蔵庫を推定する第４手順と、を含む。【選択図】図１