DATA LEARNING SERVER, AND METHOD FOR GENERATING AND USING LEARNING MODEL THEREOF

Disclosed is a data learning server according to an embodiment. The data learning server includes a communicator configured to be communicable with an external device, a learning data acquisition unit configured to acquire production information of a home appliance and operation information using th...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	TAE, Sang-jin, KIM, Tae-duk
Format:	Patent
Sprache:	eng ; fre ; ger
Schlagworte:	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES ELECTRIC COMMUNICATION TECHNIQUE ELECTRICITY PHYSICS SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR WIRELESS COMMUNICATIONS NETWORKS
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	Disclosed is a data learning server according to an embodiment. The data learning server includes a communicator configured to be communicable with an external device, a learning data acquisition unit configured to acquire production information of a home appliance and operation information using the communicator, a model learning unit configured to generate or update a learning model using the product information and the operation information, and a storage configured to store a learning model trained to estimate a new trouble detection pattern related to the trouble item as a result of the generating or updating learning model. Various embodiments are available. The data learning server may estimate a new trouble detection pattern related to a trouble of a home appliance using rule-based or AI algorithm. When estimating a region of interest using the AI algorithm, the data learning server may use machine learning, neural network, or deep learning algorithm.