AI Will Study Your Gameplay To Help Future Players, Suggests Sony’s Patent

Now players will be able to indirectly help others by using the power of AI.

Story Highlights

  • Sony has published a patent that proposes an AI that will record various gameplay choices made by gamers and suggest those strategies to the next players.
  • The proposed system will guide the new players to make efficient choices by suggesting better-graded strategies. The suggestions will directly rely on difficulty.
  • The AI may advise the players to equip different weapons, choose a different path, fight another enemy, and the like.
  • The method could also analyze the situations and recommend players to use a different character for the current obstacle for better gameplay.

Sony has recently published a patent that will record, analyze, and store various choices made by a gamer playing a title to use them as suggestions for later players in future sessions. The patent dubbed “USING DATA FROM A GAME METADATA SYSTEM TO CREATE ACTIONABLE IN-GAME DECISIONS,” will change the way players enjoy a game, as they will indirectly help subsequent users by merely playing an entry through the power of AI.

A machine learning (ML) model is used to identify successful outcomes in computer games based on aggregated game metadata including activity, mechanics, actors, statistics, and zones or locations. A strategy includes how a player over time used a character (actor) to employ one or more mechanics (weapons, vehicles) to execute various activities in various zones or locations in a computer game, with strategies being graded for success.”

The variables can include various activities, choices, weapons, methods, and the sort done by the previous gamers. The strategies adopted by old users will be graded and used as advice accordingly to future players to guide them through various hurdles.

Sony
The image reveals a block diagram that shows an example implementation of the AI model.

The accumulated data by Sony will be used to guide users traversing through the same zone in a game to make better choices. The AI may also advise players on various tried and tested ways to deal with certain in-game situations. For instance, equipping certain items before entering a dungeon may prove to be a viable approach, which the AI could recommend to future players that are entering with weaker equipment to save them.

Good strategies are then surfaced to subsequent players by, e.g., advising a player to seek a better location in a game, employ a different mechanic based on the game zone the player’s character is in such as employ a different car or car configurations, employ a plane, a particular weapon, etc.”

According to Sony, the selected difficulty level in the game will also directly influence the AI and how often it aids the player during a session. In other words, the easier the difficulty is, the more suggestions will pop up for the player on the screen. Similarly, a harder difficulty would only lead to a lower amount of assistance from the proposed method.

The image shows training and using a machine learning model to advise players in a game.

Sony will record a plethora of statistics from each player’s playthrough in various zones or locations that will inevitably influence the AI to form certain suggestions for future players. “Such statistics may include, e.g., boss kills, survival time, highest game level attained, other goals met, total enemies killed, how quickly the character died, missed shots, etc.

Thus, the different recommendations created by AI may include suggestions for taking another path to proceed, equipping a different weapon, changing the equipped armor, and more. “Example future activity can include advice to use a different character, change mechanics wielded by the character, move the character to a different game location, try a different activity, e.g., fly instead of fight.

The image shows a data flow diagram and an example implementation of AI.

Furthermore, the AI will adopt even more advanced measures to ensure differences among players are also recorded, such as the differences in characters and statistics. Sony could let gamers know how more successful players approached a certain obstacle with a different character and playstyle. As per the patent, it could offer the players to change the character or the mechanic to deal with a specific obstacle efficiently using AI.

Sony is well-renowned for publishing enticing patents, but only a few ever see the light of day. The giant conglomerate recently discussed the prospect of alerting VR users of real-life objects using dynamic notifications and 3D audio in multiple patents. 

Similar Reads: FromSoftware Has An Unannounced Project In Development Since 2022.

Did you find this article helpful?

Thanks! Do share your feedback with us. ⚡

How can we make this post better? Your help would be appreciated. ✍

Get up-to-speed gaming updates delivered right to your inbox.

We don’t spam! Read more in our privacy policy.

Source
Patentscope

Shameer Sarfaraz is a Senior News Writer on eXputer who loves to keep up with the gaming and entertainment industries devoutly. He has a Bachelor's Degree in Computer Science and several years of experience reporting on games. Besides his passion for breaking news stories, Shahmeer loves spending his leisure time farming away in Stardew Valley. VGC, IGN, GameSpot, Game Rant, TheGamer, GamingBolt, The Verge, NME, Metro, Dot Esports, GameByte, Kotaku Australia, PC Gamer, and more have cited his articles.

Experience: 4+ Years || Education: Bachelor in Computer Science.

Related Articles