Wireless communication method using on-device learning-based machine learning network

A method performed by a terminal, the method comprising:

• generating a learning list based on one or more location samples collected while the terminal communicates through a network;
• in response to detecting an event associated with one or more first items included in the learning list, acquiring training data for updating a first machine learning network to be applied to a receiver of the terminal to a second machine learning network;
• and
• updating the first machine learning network based on the training data;
• wherein the learning list includes place information and base station information distinguished for each of the one or more first items,
• wherein the place information includes spatial information regarding an application region to which the second machine learning network is completed, or a collection region for obtaining the training data,
• wherein a location sample is acquired based on the terminal entering a collection region,
• wherein one or more communication environments are determined based on applying a clustering algorithm to the one or more location samples, and
• wherein the one or more communication environments are set as items in the learning list.