REALTIME DYNAMIC MODIFICATION AND OPTIMIZATION OF GAMEPLAY PARAMETERS WITHIN A VIDEO GAME APPLICATION

摘要

Embodiments presented herein include systems and methods for performing dynamic difficulty adjustment. In addition, the embodiments disclosed herein perform dynamic difficulty adjustments using processes that are more difficult or undetectable by users compared to static and / or existing difficulty adjustment processes. In some embodiments, historical user information may be, for example, expected bounce rate, retention rate, length of time the user is expected to play the game, or the user's prediction of a historical set of users who have previously played the game. It has been used by machine learning systems to generate predictive models that predict the expected duration of game play, such as an indication of game play time. Before or during game play, the predictive model can be applied to information about the user to predict the user's expected duration of game play. Based on the expected duration, in some embodiments, the system uses a mapping data store to adjust the difficulty of the game, such as changing the values of one or more gameplay parameters to make parts of the game less difficult, for example. You can decide how to make adjustments dynamically.