Learned Model Version Comparison Display Interface

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Operators find it difficult to easily distinguish and select between multiple versions of learned models in data analysis systems, as they are often displayed in a way that makes it hard to grasp their differences at a glance, impacting the efficiency of model selection for data analysis.

Innovation Solution

A data analysis system that includes a display and controller configuration to show a selected learned model alongside its associated versions on a common screen, allowing operators to easily compare and select the appropriate model for analysis, with features like version history and accuracy evaluation screens for better decision-making.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If multiple different versions of learned models are displayed on the display, then operators can select from multiple models, but operators cannot easily grasp the plurality of different versions at a glance

Engineering Contradiction:
Improvemodel selection capabilityVSAvoidmodel version comprehension
Core Design Contradiction:
Adaptability or versatilityVSEase of operation

Solution Approach 1:

The display is segmented into multiple regions: a first display region showing learned models for different analysis purposes and a second display region showing version information. This segmentation allows operators to view multiple model versions while maintaining clear organization and easy comprehension through spatial separation of model identifiers and their version details.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Version information is displayed in an additional dimension (second display region) separate from the main model list. This dimensional addition allows operators to perceive version differences without cluttering the primary model selection view, enabling both comprehensive model browsing and easy version differentiation.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Quantity of substance

If a list of learned models is displayed, then multiple models can be shown, but the complexity of the display increases making it harder to grasp differences

Engineering Contradiction:
Improvenumber of models displayedVSAvoiddisplay complexity
Core Design Contradiction:
Quantity of substanceVSDevice complexity

Solution Approach 1:

The display is divided into distinct regions: the first display region presents learned models in an organized manner while the second display region handles version information separately. This segmentation reduces overall display complexity by preventing information crowding and maintaining clear visual hierarchy.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Version information is extracted from the main model list and displayed in a separate second display region. This extraction prevents version details from cluttering the primary model display, allowing operators to view multiple models without being overwhelmed by version complexity.

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentUS20240362904A1Data analysis system, data analysis apparatus and data analysis method
Publication Date: 2024.10.31 SHIMADZU CORP
  • US20240362904A1 patent drawing
  • US20240362904A1 patent drawing
  • US20240362904A1 patent drawing

AI summary

A data analysis system according to this invention includes a data acquirer; an analyzer configured to analyze a to-be-analyzed data by using a learned model; a learned model producer configured to produce the learned model; a storage configured to store each of a plurality of learned models associated with a different version(s) of learned model(s) that is/are other learned model(s) of the plurality of learned models; a display configured to display the learned models; and a controller configured to control the display to display a selected learned model, and the different version(s) of learned model(s) that is/are associated with the selected learned model on a common screen.