Using data from a game metadata system to create actionable in-game decisions
US12145064B2 · kind B2 · utility
Assignee
Inventor
Key dates
| Filing date | Sep 12, 2021 |
| Grant date | Nov 19, 2024 |
| Priority date | — |
| Expiry date | Dec 25, 2041 |
Classification
- Technology area (CPC A)Human Necessities
- CPC primaryA63F2300/5533
- WIPO fieldFurniture, games
- WIPO sectorOther fields
Abstract
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. 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.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.