Automatic Excretion Processing Device Using Deep Learning Classification

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing automatic excretion-processing devices are inadequate for determining the state of solid objects excreted by care-requiring individuals, placing a significant burden on care workers.

Innovation Solution

An automatic excretion-processing device equipped with a cup, processing unit, acquisition unit, and determination unit that uses iterative learning and deep learning with convolutional neural networks to classify the state of excreted objects based on captured images, reducing the need for manual inspection and improving labor efficiency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual inspection of excreted objects is performed by care workers, then accurate determination of object state can be achieved, but the burden on care workers increases and labor efficiency decreases

Engineering Contradiction:
Improvedetermination accuracy of object stateVSAvoidlabor efficiency of care workers
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The system enables automatic determination of excreted object states through image acquisition and deep learning processing, allowing the device to serve itself rather than requiring care workers to perform manual inspection. The determination unit automatically classifies object states based on captured images, eliminating the need for human intervention in the determination process.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical/manual inspection process with an automated image processing system. The acquisition unit captures images of excreted objects, and the determination unit uses deep learning algorithms to analyze these images and determine object states, substituting human visual inspection with an automated optical and computational system.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Ease of operation

If automated image processing is implemented to determine object state, then the burden on care workers is reduced, but the device complexity increases

Engineering Contradiction:
Improveease of operation for care workersVSAvoidcomplexity of determination system
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The acquisition unit serves as an intermediary between the excreted objects and the determination unit. It captures images of the objects and transmits them to the determination unit for analysis, acting as a mediator that simplifies the interface between the physical object and the complex processing system.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The determination unit performs preliminary classification of object states based on captured images before care workers need to review the information. By pre-processing and determining object states automatically, the system prepares information in advance, reducing the operational burden on care workers despite the underlying system complexity.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS20230172744A1Automatic excretion-processing device, management system, determination method, and program
Publication Date: 2023.06.08 LIBERTYSOLUTION CO LTD
  • US20230172744A1 patent drawing
  • US20230172744A1 patent drawing
  • US20230172744A1 patent drawing

AI summary

An automatic excretion-processing device (1) includes a cup (2) attached to a human body and configured to receive an object which is excreted from the human body, a processing unit (3) configured to transfer the object in the cup outside of the cup, an acquisition unit (4) configured to image the inside of the cup and to acquire a captured image of the object, and a determination unit (5) configured to extract a feature of the object with reference to a result of iterative learning using the captured images of the object in different states on the basis of the captured images acquired by the acquisition unit and to classify the state of the object.