Abstract: An apparatus for training a document summarization model includes a token generation unit, a named entity recognition unit, and a model training unit. The token generation unit generates document tokens and summarization tokens. The named entity recognition unit assigns named entity token status to a summarization token, recognized as a named entity through NER, and assigns non-named entity token status to the other tokens. The model training unit obtains feature vectors by inputting the plurality of document tokens into an encoder inside a document summarization model, obtains a first loss related to the named entity token, a second loss related to the other tokens, and a total loss using a weighted value by inputting the feature vectors, the summarization tokens, the named entity token, and the non-named entity token into a decoder inside the document summarization model, and trains the document summarization model on the basis of the total loss.

Abstract: An apparatus for training a dialogue summary model according to an embodiment includes a parameter transferer configured to transfer one or more learning parameter values of a pre-trained natural language processing model to a sequence-to-sequence-based dialogue summary model, and a model trainer configured to train the dialogue summary model by using the transferred learning parameter values as initial values for learning parameters of each of an encoder and a decoder in the dialogue summary model.

Abstract: An apparatus and a method for setting a combination desired temperature for a plurality of air conditioners installed in a target zone, and a method for calculating base relationship information of the target zone include setting a combination desired temperature of a top-priority air conditioner among the air conditioners by at least one test driving of the top-priority air conditioner, the combination desired temperature of the top-priority air conditioner being a desired temperature of the top-priority air conditioner for realizing a comfortable temperature range of the target zone; and in response to a temperature of at least one temperature sensor among temperature sensors being outside the comfortable temperature range while the top-priority air conditioner is driven at the combination desired temperature of the top-priority air conditioner, adjusting the combination desired temperature of the first air conditioner through test driving of the first air conditioner.

Abstract: An apparatus and a method for predicting an amount of temperature change of a target zone are provided. The method includes collecting a plurality of base information, and calculating base relationship information between an indoor/outdoor temperature difference of the target zone and an amount of temperature change of the target zone on the basis of the plurality of base information. Each of the plurality of base information is information on the amount of temperature change of the target zone according to the indoor/outdoor temperature difference of the target zone during a late night time section, and the late night time section is set on the basis of at least one of activity schedule information, a sunrise time point, and a sunset time point of the target zone.

Abstract: An apparatus and a method for predicting an amount of temperature change of a target zone are provided. The method includes collecting a plurality of base information, and calculating base relationship information between an indoor/outdoor temperature difference of the target zone and an amount of temperature change of the target zone on the basis of the plurality of base information. Each of the plurality of base information is information on the amount of temperature change of the target zone according to the indoor/outdoor temperature difference of the target zone during a late night time section, and the late night time section is set on the basis of at least one of activity schedule information, a sunrise time point, and a sunset time point of the target zone.

Abstract: Disclosed is a hybrid drying system where a cold-air drier and a desiccant drier are combined to increase drying efficiency (extent of dehumidification/power consumption), thereby shortening drying time and significantly reducing operation costs. The hybrid drying system includes a desiccant drier installed between an evaporator and a condenser and having an absorbing part configured to produce dry air from the cold-air dried air which has passed through the evaporator and a detaching part configured to supply recycled air heated by the condensation heat of the condenser as a recycling heat source; a heat exchanger configured to heat-exchange exterior air with recycled exhaust air with the recycled air to retrieve exhaust heat; and a control unit configured to simultaneously control a cold-air drying operation and a desiccant drying operation according to the humidity and temperature of the drying chamber.

Abstract: Disclosed is a hybrid drying system where a cold-air drier and a desiccant drier are combined to increase drying efficiency (extent of dehumidification/power consumption), thereby shortening drying time and significantly reducing operation costs. The hybrid drying system includes a desiccant drier installed between an evaporator and a condenser and having an absorbing part configured to produce dry air from the cold-air dried air which has passed through the evaporator and a detaching part configured to supply recycled air heated by the condensation heat of the condenser as a recycling heat source ; a heat exchanger configured to heat-exchange exterior air with recycled exhaust air with the recycled air to retrieve exhaust heat; and a control unit configured to simultaneously control a cold-air drying operation and a desiccant drying operation according to the humidity and temperature of the drying chamber.