Over the past months, multiple patents have come up describing Sony’s possible future plans for PlayStation. A patent we uncovered earlier described a system that allows players to leave helpful in-game notes for each other. Now, Sony has filed another patent, similar in nature, but works differently from the one we discussed a few weeks ago.
It looks like Sony is designing a self-learning neural system for PlayStation. The system will study player behavior and interactions in the game and offer helpful tips and hints. Optionally, the player can choose to allow the neural system to study behaviors in previously played games.
Generally, a video game and video game assistance are adapted to a player. For example, a narrative of the video game is personalized to an experience level of the player. Similarly, assistance in interacting with a particular context of the video game is also personalized. The personalization learns from historical interactions of players with the video game and, optionally, other video games. In an example, a deep learning neural network is implemented to generate knowledge from the historical interactions. The personalization is set according to the knowledge.
The images show a very basic implementation of the system, however, according to the patent, it is intended to be used in more complete video games such as open-world RPGs. The helpful tips will guide players in the right direction and predict if you’ll need help in an upcoming section of the game. For example, if you have a history of being stuck of boss fights, expect tips and tricks throughout your next boss encounter. On the other hand, if you’re the type of player who has trouble figuring out puzzles, the game will help you out. Of course, everything here is optional so you can choose to turn it off.
As is the case with other patents filed by Sony, this one might not ever see actually implementation. However, it is nice to see Sony working on advancing such features in its video games and consoles.