Gaming Attract Mode Content Using Self-Evolving Generative AI

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional intelligent agents in gaming systems struggle to provide personalized and engaging attract mode content due to their inability to self-evolve and adapt to individual player preferences, leading to inefficient player engagement and increased computational costs.

Innovation Solution

Implement self-evolving AI-based generative models that generate personalized attract mode content by analyzing player preferences and gaming system data, allowing for real-time content generation and adaptation based on player behavior and system state, while conserving processing resources.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If conventional intelligent agents are used to provide attract mode content, then the system structure is simple, but the player engagement is insufficient and content is not personalized

Engineering Contradiction:

Improveplayer engagementVSAvoidsystem complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The intelligent agent performs self-evolution by automatically analyzing player behavior data and updating its own content generation capabilities without external intervention. The agent monitors player interactions with generated content and uses this feedback to refine future content creation, enabling the system to adapt to player preferences autonomously over time

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system implements a feedback loop where player behavior data from attract mode interactions is collected, analyzed, and used to train and improve the intelligent agent's content generation models. This continuous feedback mechanism enables the agent to learn from player responses and evolve its content creation strategies to enhance engagement

Inventive Principle:

Principle #23Feedback

2Adaptability or versatility

If AI-based generative models are used to generate personalized content, then player engagement is enhanced, but computational costs increase

Engineering Contradiction:

Improvecontent personalizationVSAvoidcomputational cost

Core Design Contradiction:

Adaptability or versatilityVSUse of energy by moving object

Solution Approach 1:

The system generates multiple potential content options using the AI generative model and then applies filtering and selection mechanisms to identify the most suitable content for each player. This partial action approach uses computational resources more efficiently by not exhaustively generating all possible content variations, but rather generating a manageable set and selecting from those

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The intelligent agent performs preliminary analysis of player behavior data and pre-generates content variations before actual player interaction. By preparing and pre-filtering content options in advance based on predicted player preferences, the system reduces real-time computational requirements during actual attract mode operation

Inventive Principle:

Principle #10Preliminary action

3Adaptability or versatility

If real-time content generation is implemented, then player engagement is improved, but processing latency increases

Engineering Contradiction:

Improvecontent adaptationVSAvoidprocessing latency

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The system performs preliminary content generation and preparation tasks before player interaction occurs. By pre-generating content variations and pre-analyzing player data in advance, the system reduces the processing time required during actual attract mode operation, enabling faster response to player interactions while maintaining personalization

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system dynamically adjusts the level of real-time content generation based on player interaction intensity and system state. During low-activity periods, the system performs deeper analysis and generates more varied content options in advance. During high-activity periods, it uses pre-generated content with minimal real-time processing, creating a dynamic balance between personalization and processing speed

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS20260030958A1System and method facilitating generative artificial intelligence attract modes

Publication Date: 2026.01.29 INTERNATIONAL GAME TECHNOLOGY INC

AI summary

The present disclosure relates generally to a gaming system, device, and method that, in response to a detected content generation event, generate a prompt from a set of content preferences associated with a selected player, send the prompt to a generative model; select at least a portion of the received content for attract mode presentation by a gaming device; and cause the received attract mode content to be presented by the gaming device to the a player.