Neural Network NPC Behavior Adaptation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for generating and utilizing non-player characters (NPCs) in multiplayer video games are robotic and lack the fluidity and creative interaction exhibited by human players, failing to provide personalized and evolving gaming experiences.

Innovation Solution

A computer-implemented method and system that uses neural networks or machine learning processes to generate and modify NPCs by tracking human player profiles and game data, allowing NPCs to mimic human behavior, evolve, and adapt in real-time, thereby enhancing gameplay experience.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If NPCs are programmed with fixed AI behaviors to fill gameplay gaps, then gameplay completeness is improved, but NPC authenticity and player engagement deteriorate

Engineering Contradiction:
Improvegameplay completenessVSAvoidNPC robotic behavior
Core Design Contradiction:
Adaptability or versatilityVSObject-generated harmful factors

Solution Approach 1:

The patent applies dynamics by transitioning from static AI behaviors to dynamic, evolving NPC personalities. Each NPC is assigned a personality profile that can change over time based on interactions with human players, allowing NPCs to adapt their behavior patterns, communication styles, and gameplay strategies dynamically rather than following fixed scripts.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system implements feedback mechanisms where NPC behaviors are continuously monitored and adjusted based on player responses. Player interactions provide feedback that feeds into the NPC evolution process, allowing NPCs to learn from their interactions and refine their personalities, thereby reducing robotic behavior while maintaining gameplay completeness.

Inventive Principle:
Principle #23Feedback

2Device complexity

If NPCs are made generic to simplify programming, then development complexity is reduced, but player personalization and engagement deteriorate

Engineering Contradiction:
ImproveNPC programming complexityVSAvoidNPC personalization
Core Design Contradiction:
Device complexityVSAdaptability or versatility

Solution Approach 1:

The patent segments NPC personalities into distinct profiles with specific attributes, skills, and behavioral patterns. Instead of programming each unique NPC from scratch, the system uses a library of personality templates that can be combined and modified to create diverse NPCs, reducing programming complexity while enabling personalization.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system utilizes parameter changes by adjusting key attributes of NPC profiles (such as skill levels, personality traits, and behavioral parameters) to create personalized NPCs. Rather than requiring complex programming for each unique NPC configuration, the system modifies existing parameters to generate tailored NPC experiences for different players.

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If NPCs use fixed skill levels to match players, then matching accuracy is improved, but gameplay fluidity and creativity deteriorate

Engineering Contradiction:
Improveskill level matchingVSAvoidgameplay fluidity
Core Design Contradiction:
Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent applies dynamics by making skill levels dynamic rather than static. NPCs start with initial skill levels based on player matching but continuously evolve their skills through gameplay interactions. This allows NPCs to adapt their skill levels in real-time, providing fluid and creative gameplay while maintaining accurate initial matching.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system implements continuous skill evolution where NPCs constantly learn and improve their skills throughout the gameplay session. This continuous action ensures that skill matching remains accurate while gameplay fluidity is maintained, as NPCs are always adapting their abilities rather than sticking to fixed skill levels.

Inventive Principle:
Principle #20Continuity of useful action

Data Source

PatentUS20230338853A1Generating Improved Non-Player Characters Using Neural Networks
Publication Date: 2023.10.26 ACTIVISION PUBLISHING INC
  • US20230338853A1 patent drawing
  • US20230338853A1 patent drawing
  • US20230338853A1 patent drawing

AI summary

The disclosed systems and methods track and continuously monitor data about a player or a multiple players and create a non-playing character (NPC) and/or modify an existing NPC that replicates the player(s) play style. The disclosed systems implement an artificial intelligence engine that monitors how a real player responds to one or more events in a game and correlates game outcomes with real player actions, with the actions or reactions of third players, and/or with an amount or extent of engagement. The engine may be used to generate, host, or otherwise provide data representative of one or more NPCs to multiple different games, being hosted by one or more servers, concurrently.