ML-Based Access Component Coordination for Error Reduction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing access systems often have combinations of components that are not optimally coordinated, leading to increased susceptibility to errors and maintenance needs, which can be unnoticed during the planning phase, resulting in inefficiencies and higher costs.

Innovation Solution

A method using a machine learning system to analyze plan data and generate suggestions for optimizing access component combinations, including replacing individual components or adjusting parameters to extend service life and reduce maintenance efforts, by predicting potential issues and providing change or new suggestions based on architectural, security, and usage frequency information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If access components are selected during the planning phase without ML analysis, then the planning process is simple and quick, but the component combinations may not be optimally coordinated leading to increased susceptibility to errors and maintenance needs

Engineering Contradiction:
Improvecoordination of access component combinationsVSAvoidplanning process complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The ML system performs analysis of access component combinations during the planning phase, before the system is installed. This preliminary action identifies potential coordination issues and suggests optimizations in advance, preventing problems before they occur rather than detecting them during operation or maintenance.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent replaces manual expert review of access component combinations with an automated ML system. The machine learning model analyzes plan data, component specifications, and compatibility rules to evaluate coordination quality, substituting human expertise with automated intelligent analysis that can process multiple components simultaneously.

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

2Reliability

If ML analysis is performed on plan data to generate optimization suggestions, then component coordination and reliability are improved, but additional time and computational resources are required during planning

Engineering Contradiction:
Improveaccess system coordinationVSAvoidplanning phase duration
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The ML analysis is performed during the planning phase while the system is still being designed, allowing time for multiple iterations and optimizations. By conducting the analysis early, the patent avoids later time-consuming adjustments during installation or maintenance, and suggestions can be incorporated into the final plan before deployment.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The ML system analyzes digital plan data and component specifications rather than physical components. This virtual analysis of copied information allows rapid evaluation of multiple component combinations without physical prototyping or installation, significantly reducing the time penalty compared to traditional manual review methods.

Inventive Principle:
Principle #26Copying

3Productivity

If non-optimal access component combinations are installed, then initial installation is faster, but maintenance effort and costs increase over time

Engineering Contradiction:
Improveinstallation speedVSAvoidmaintenance effort
Core Design Contradiction:
ProductivityVSEase of repair

Solution Approach 1:

The ML system identifies and flags potential maintenance issues during the planning phase, before installation occurs. By detecting coordination problems early, the system allows planners to select alternative component combinations that are more maintainable, preventing the installation of systems that would require excessive maintenance effort later.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The ML analysis provides feedback on the planned component combinations, evaluating their coordination quality and predicting maintenance requirements. This feedback loop allows planners to adjust their selections based on automated assessments, ensuring that the final installed system balances installation efficiency with long-term maintainability.

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP4280095A1Method for generating proposals relating to one or more access system components of an access system; computer system; training data; computer program product
Publication Date: 2023.11.22 DORMAKABA SCHWEIZ AG
  • EP4280095A1 patent drawingFigure 1A~3B
  • EP4280095A1 patent drawingFigure 4
  • EP4280095A1 patent drawingFigure 5

AI summary

The invention relates to a method for generating proposals concerning one or more access components of an access system using a machine learning (ML) system, wherein the method for generating proposals comprises: --- a1) Obtaining plan data of a property by the ML system, wherein the plan data relates to the planning phase of the property and/or an access system of the property, --- a2) Analyzing the plan data using the ML system to generate at least one proposal concerning one or more access components of the access system of the property.