Laundry treatment appliance and method of using the same according to matched laundry loads
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional laundry treatment appliances incur fixed costs regardless of load size, leading to inefficiencies and resource wastage when handling fractional loads, particularly in public laundromats.
Innovation Solution
A laundry treatment appliance equipped with a machine learning image recognition model analyzes user laundry loads, matches users with similar loads, and generates a joint washing cycle to distribute costs evenly among multiple users.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a fixed fee is charged for each washing operation regardless of load size, then the appliance can operate simply without complex matching systems, but resource waste increases and cost efficiency deteriorates
Solution Approach 1:
The patent combines multiple fractional laundry loads into a single consolidated washing cycle by matching users with compatible loads. The controller receives images of different laundry loads, analyzes them for compatibility (colors, fabric types, load sizes), and merges them into joint washing cycles that fully utilize the appliance capacity, thereby reducing energy and water waste per unit of laundry processed
Solution Approach 2:
The system changes operational parameters by transitioning from fixed-fee single-user cycles to variable-fee multi-user joint cycles. The controller dynamically adjusts washing parameters (water volume, energy consumption, cycle duration) based on the combined load characteristics, optimizing resource usage while maintaining washing quality across different load compositions
2Reliability
If users separate laundry into like categories, then washing quality is maintained, but load size becomes fractional and cost efficiency worsens
Solution Approach 1:
The patent merges multiple fractional loads from different users into consolidated washing cycles while preserving category separation. The image recognition system analyzes each load's characteristics (colors, fabric types) and matches compatible loads together, ensuring that washing quality requirements are met while achieving full appliance utilization and improved cost efficiency
Solution Approach 2:
The system segments the laundry washing process into distinct matching phases: individual load assessment through image analysis, compatibility evaluation based on washing requirements, and selective combination into joint cycles. This segmentation allows maintenance of washing quality standards while optimizing load consolidation for cost efficiency
3Loss of energy
If a machine learning image recognition model is implemented to match laundry loads, then resource efficiency improves through optimal matching, but device complexity increases
Solution Approach 1:
The patent replaces manual laundry assessment and matching with an automated machine learning image recognition system. The controller captures images of laundry loads and uses trained models to automatically analyze characteristics (colors, fabric types, load sizes), eliminating the need for manual evaluation and enabling efficient, objective matching that optimizes resource efficiency while managing system complexity through automation
4Ease of operation
If fractional loads are washed separately, then washing operations are simple to manage, but cost per load increases and resource utilization worsens
Solution Approach 1:
The system implements self-service automated load matching where the controller independently assesses incoming laundry loads, matches them with compatible loads from other users, and consolidates them into optimal washing cycles without requiring user intervention. This maintains ease of operation for individual users while achieving improved cost efficiency through automated resource optimization
Data Source
AI summary
A laundry treatment appliance includes a cabinet; a wash tub; a wash basket; and a controller provided within the cabinet to direct a laundry operation. The laundry operation includes receiving a plurality of wash requests from a plurality of unique users, wherein each wash request of the plurality of wash requests comprises an image of a unique laundry load; analyzing, by one or more computing devices using a machine learning image recognition model, each image to evaluate one or more laundry load characteristics of a first unique laundry load and a second unique laundry load; matching a first unique user and a second unique user from the plurality of users, the first user and the second user having a matching laundry load characteristic from the one or more laundry load characteristics; and generating a joint washing cycle subsequent to matching the first and second unique users.