Neural Network Object Compatibility Analysis for Digital Environments

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional techniques for creating targeted digital content are limited by user reluctance to provide information, reliance on inaccurate metadata, and ineffective product recommendations based on similarity with other users' data, leading to irrelevant content delivery.

Innovation Solution

The system uses neural networks to analyze two-dimensional digital representations of real-world environments, identifies real-world objects, and determines the least compatible object within a viewpoint using style and color incompatibility, replacing it with product recommendations that match the surrounding environment's style and color compatibility, generating personalized and contextually relevant content.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If conventional techniques use user-provided information for targeted content delivery, then personalization is improved, but user privacy concern and data accuracy deteriorate

Engineering Contradiction:

ImprovepersonalizationVSAvoiddata accuracy

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The system performs self-service by automatically analyzing visual environment data without requiring user information input. The neural network detects objects, determines compatibility, and generates personalized content recommendations autonomously, eliminating the need for users to provide personal data while maintaining personalization capabilities.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical system of user information collection and manual profiling with an automated visual analysis system using neural networks. The system substitutes traditional data gathering methods with image-based environmental analysis, achieving personalization through visual compatibility assessment rather than user-provided data.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Ease of manufacture

If conventional techniques rely on metadata for product recommendations, then implementation simplicity is improved, but recommendation accuracy deteriorates

Engineering Contradiction:

Improveimplementation simplicityVSAvoidrecommendation accuracy

Core Design Contradiction:

Ease of manufactureVSMeasurement precision

Solution Approach 1:

The system replaces metadata-based recommendation mechanisms with neural network-based visual analysis. Instead of relying on text tags and categorical data, the system uses image processing to directly assess style and color compatibility of objects in the user's environment, significantly improving recommendation accuracy through visual perception rather than textual metadata.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Adaptability or versatility

If conventional techniques use user browsing history for content delivery, then contextual relevance is improved, but user privacy requirement deteriorates

Engineering Contradiction:

Improvecontextual relevanceVSAvoiduser privacy requirement

Core Design Contradiction:

Adaptability or versatilityVSObject-affected harmful factors

Solution Approach 1:

The system achieves contextual relevance through self-service environmental analysis rather than user history tracking. By automatically analyzing the visual content of the user's environment and determining object compatibility, the system generates contextually relevant recommendations without accessing or storing any user personal information or browsing history.

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS10984467B2Compatibility-based identification of incompatible objects in digital representations of real-world environments

Publication Date: 2021.04.20 ADOBE INC

AI summary

The technology described herein is directed to object compatibility-based identification and replacement of objects in digital representations of real-world environments for contextualized content delivery. In some implementations, an object compatibility and retargeting service that selects and analyzes a viewpoint (received from a user's client device) to identify objects that are the least compatible with other surrounding real-world objects in terms of style compatibility with the surrounding real-world objects and color compatibility with the background is described. The object compatibility and retargeting service also generates recommendations for replacing the least compatible object with objects/products having more style/design compatibility with the surrounding real-world objects and color compatibility with the background. Furthermore, the object compatibility and retargeting service can create personalized catalogues with the recommended objects/products embedded in the viewpoint in place of the least compatible object with similar pose and scale for retargeting the user.