Information Processing Device Dissimilar String Selection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing information processing technologies fail to effectively distinguish and avoid applying character strings with similar meanings to electronic information, leading to inefficiencies in representing content.

Innovation Solution

An information processing device with a computation unit to compute similarity between character strings and an association unit that selects and associates dissimilar character strings as representative strings, using machine learning models like encoder-decoder neural networks and bidirectional long short-term memory (Bi-LSTM) to rank and evaluate character strings for dissimilarity.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If multiple character strings are generated from electronic information, then content representation completeness is improved, but redundancy of similar meaning character strings increases

Engineering Contradiction:
Improvecontent representation completenessVSAvoidcharacter string redundancy
Core Design Contradiction:
Loss of informationVSQuantity of substance

Solution Approach 1:

The patent extracts only the necessary representative character string from multiple generated candidates by computing similarity metrics and selecting the most dissimilar string. This removes redundant character strings with similar meanings while preserving the essential content representation, directly addressing the contradiction between completeness and redundancy.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent changes the parameter of character string selection from random or simple ranking to similarity-based selection. By computing similarity parameters between character strings and using these parameters to guide selection, the system optimizes the balance between representing complete content and avoiding redundancy.

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If similarity computation is performed between character strings, then selection accuracy of representative strings is improved, but processing time increases

Engineering Contradiction:
Improveselection accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs similarity computation only between necessary character string pairs rather than all possible combinations. By computing similarity incrementally and stopping when a representative string is found, the system achieves sufficient selection accuracy without the excessive processing time of complete pairwise comparison.

Inventive Principle:
Principle #16Partial or excessive action

3Manufacturing precision

If representative character strings are selected based on dissimilarity, then content representation quality is improved, but device complexity increases

Engineering Contradiction:
Improvecontent representation qualityVSAvoidprocessing system complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The patent introduces a computation unit as an intermediary that handles the complex similarity computation task. This mediator component simplifies the overall system architecture by centralizing the dissimilarity-based selection logic, making the complex process manageable and maintainable while achieving high content representation quality.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentUS10936901B2Information processing device and non-transitory computer readable recording medium
Publication Date: 2021.03.02 FUJIFILM BUSINESS INNOVATION CORP
  • US10936901B2 patent drawing
  • US10936901B2 patent drawing
  • US10936901B2 patent drawing

AI summary

An information processing device includes a computation unit that computes a similarity between character strings among plural character strings which express a content of electronic information and which are generated from the electronic information, and an association unit that associates a dissimilar character string that is not similar to another character string among the plural character strings with the electronic information as a representative character string that expresses the electronic information.