New PS5 Details Hint At Console That Learns From Players

[Nergal]

 

 

With PlayStation 5 rumors in full swing, a new set of details emerging from a patent Sony filed back in October of last year seems to suggest the console will be even more powerful than previous hints made it out to be. The latest patent hints at a console that will be able to learn from the players who are using it, customizing the play experience to better suit the device's owner.

The PlayStation 5 has been the subject of a lot of speculation recently thanks to rumors that began to gain traction late last year. Those rumors suggested that the console would be getting revealed at some point in 2019 with a 2020 launch date to follow. The timing of that announcement would make sense: the PlayStation 4's weaker profits in 2018 indicate a need to begin thinking about the company's next-generation device more seriously, and it would give Sony's competitors less time to close the gap that the PS4 opened up on its competitors in the current console generation.

According to YouTuber Skullzi, a relatively recent patent from Sony strongly indicates that the PS5 will place a heavy emphasis on the customization of games and game experiences. During the video, Skullzi highlights the fact that the patent features a "deep learning neural network" that will be able to learn from a player's past actions. While certain games have used similar technology in the past, the implementation of this feature into an entire console would certainly be something new. Here's what the patent's abstract says about the potentially new Sony console tech:

"Generally, a video game and video game assistance are adapted to a player. For example, a narrative of the video 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."