Disclosed is a method of predicting the lifespan of a filter in an air cleaner based on machine learning. According to an embodiment of the present disclosure, a machine learning-based filter lifespan prediction method may more precisely predict the lifespan of a filter in an air cleaner by inputting fine dust concentration data and a history related to use of the air cleaner to a lifespan prediction model and determining the purifying efficiency and exchange time of the filter according to an output value. Intelligent air cleaner of the present disclosure can be associated with artificial intelligence modules, drones (unmanned aerial vehicles (UAVs)), robots, augmented reality (AR) devices, virtual reality (VR) devices, devices related to 5G service, etc.