Gameplay Analysis for Content Recommendations

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing content recommendation systems for gaming content do not effectively account for a user's specific gameplay interactions and preferences, often recommending games based on the primary genre rather than the user's actual gameplay habits, leading to irrelevant suggestions.

Innovation Solution

A system utilizing computer vision and machine learning-based techniques to analyze gameplay video and audio, generating keywords that reflect a user's preferred gameplay types, which are then used to recommend content that aligns with their interests, such as golf or driving games, rather than general adventure or shooter games.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If content recommendation is based on game genre classification, then recommendation speed is improved, but recommendation accuracy deteriorates

Engineering Contradiction:

Improverecommendation speedVSAvoidrecommendation accuracy

Core Design Contradiction:

SpeedVSMeasurement precision

Solution Approach 1:

The patent segments gameplay into multiple distinct dimensions including primary gameplay, secondary gameplay, mini-games, and side activities. Each dimension is analyzed separately to capture different aspects of user preference, transforming a single coarse-grained genre classification into multiple fine-grained gameplay type classifications that together provide both speed and accuracy.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent applies local quality by making recommendation accuracy context-dependent on the specific gameplay dimension being analyzed. Different gameplay dimensions (primary, secondary, mini-games) are evaluated with appropriate weighting and specificity, allowing the system to provide accurate recommendations for each aspect while maintaining overall system efficiency.

Inventive Principle:

Principle #3Local quality

2Measurement precision

If content recommendation analyzes detailed gameplay interactions, then recommendation accuracy is improved, but computational complexity deteriorates

Engineering Contradiction:

Improverecommendation accuracyVSAvoidcomputational complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent divides complex gameplay analysis into separable dimensions (primary gameplay, secondary gameplay, mini-games, side activities). Each dimension can be processed independently using specialized analysis techniques, reducing the overall computational complexity compared to analyzing all gameplay elements uniformly.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent implements partial action by selectively analyzing gameplay dimensions based on their relevance to user preference. Not all gameplay elements are analyzed with the same depth - the system focuses computational resources on the most informative dimensions while using lighter analysis for less critical aspects.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS20210064965A1Content recommendations using one or more neural networks

Publication Date: 2021.03.04 NVIDIA CORP

AI summary

Apparatuses, systems, and techniques to determine content recommendations for a user. In at least one embodiment, one or more game recommendations are determined based upon interactions of a player with a game.