A numerical controller includes a machine learning device for performing machine learning of machining condition adjustment of a machine tool. The machine learning device calculates a reward based on acquired machining-state data on a workpiece, and determines an adjustment amount of machining condition based on a result of machine learning and machining-state data, and adjusts machining conditions based on the adjustment amount. Further, the machine learning of machining condition adjustment is performed based on the determined adjustment amount of machining condition, the machining-state data, and the reward.

A server for providing an artificial intelligence (AI)-based adaptive feed amount, includes a memory, a communication module that communicates with at least one machine tool, and at least one processor that communicates with the memory and the communication module, wherein the at least one processor is configured to receive an initial reasonable load value from a first machine tool in a unit factory, to obtain at least one of a first recommended feed change amount, a first recommended tool or base-material rotation speed, or a first recommended cut-in amount by inputting a target load value and the initial reasonable load value of the first machine tool to a first AI model, and to transmit, to the first machine tool.