Inclusive Product Design Using Persona-Level ML Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional product design methods fail to adequately consider demographic and individual preferences, leading to unsuitable product designs that can decrease sales and fail to learn from customers on an ongoing basis, resulting in poor product decisions.
Innovation Solution
A system using multi-level machine learning models to determine likeness, inclusivity, and feature importance scores, combined with multisensory reviews, to iteratively enrich survey data for inclusive product design.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If conventional test methods are used to gather customer feedback, then product design decisions can be made with some customer input, but the process is labor-intensive, expensive, and cannot capture ongoing customer needs and preferences
Solution Approach 1:
The patent replaces conventional mechanical research methods (focus groups, surveys, field trials) with an automated electronic system that uses machine learning models to analyze customer feedback from multiple digital sources including social media, reviews, and usage data. This substitution eliminates the need for labor-intensive manual studies while continuously capturing customer information.
Solution Approach 2:
The system enables customers to provide feedback automatically through their natural digital interactions (purchases, reviews, social media posts, usage patterns) without requiring their active participation in studies. The machine learning system processes this self-generated data to continuously inform product design decisions.
2Productivity
If product development speed is increased to meet market demands, then time to market is reduced and productivity improves, but the ability to conduct meaningful customer studies and measure complexity deteriorates
Solution Approach 1:
The patent implements continuous automated analysis of customer feedback through machine learning models that process data in real-time from multiple sources. This continuous action replaces periodic manual studies, allowing product development to proceed at high speed while maintaining precise measurement of customer needs through ongoing data collection and analysis.
3Quantity of substance
If product design focuses on a target population sample, then design decisions can be made with sufficient data, but inclusivity for other demographic groups deteriorates leading to decreased sales
Solution Approach 1:
The patent creates a universal machine learning system that analyzes customer feedback across all demographic groups simultaneously rather than studying separate segments. The model identifies patterns and preferences across diverse populations, enabling product designs that serve multiple demographic groups effectively and improve inclusivity while maintaining data quantity.
Data Source
AI summary
Systems and methods for inclusive product design are disclosed. The system obtains likeness score for product attributes for product using survey before design phase of product, from user(s), and determines impact and relative contribution of each product attribute, for user, to inclusivity score, using multi-level machine learning models. The system segregates product attributes and inclusivity score at persona level, and determines feature importance score of each feature in product attributes for each user. System calculates risk score for each user indicating sensibility towards product designer choices, and provides what-if analysis capabilities to product designer for analyzing, based on risk score, risk of each user with sensibility towards product designer choices and receives multisensory review from user. The system computes overall score by combining feature importance and inclusivity scores, facial coding, voice tonality, and haptics feedback, to granular level and outputs iteratively enriched survey data for inclusive designing of products.