How to generate a trained model to predict the action the user chooses, etc.

Abstract

PROBLEM TO BE SOLVED: To provide a method capable of generating a trained model for predicting an action selected by a user in an arbitrary game state. A method according to an embodiment of the present invention generates a trained model for predicting an action selected by a user in a game in which the game progresses according to an action selected by the user and the game state is updated. This is a method for generating a game state text and an action text, which are text data expressed in a predetermined format, from the game state and action data included in the history data related to the game, and one game state and the one. Includes a step to generate training data containing a pair of game state text and action text corresponding to a pair of selected actions in the game state of, and a step to generate a trained model based on the generated training data.

Full Text: Google Patents