Provided are a server and a method for generating data for cooking food. The method may include: obtaining text indicating a food recipe; applying the text to each of a plurality of natural language understanding (NLU) models for analyzing the text; identifying a plurality of semantic elements included in the text based on at least one semantic element that is output from each of the plurality of NLU models; generating first machine readable recipe (MRR) data structured to include a plurality of cooking device control parameters, by using the plurality of semantic elements; obtaining log data of a user related to a device control action performed by the user to operate a cooking device; and generating second MRR data personalized to the user, by updating the plurality of cooking device control parameters, based on the log data.