Institutional Knowledge Integration for Fuzzy Data and AI Prediction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current data-driven decision-making and prediction methods struggle with integrating diverse data types such as static, dynamic, and fuzzy data, which are often imprecise and ambiguous, leading to unreliable institutional knowledge and suboptimal decision-making and prediction accuracy.

Innovation Solution

A method integrating quantitative and qualitative predictive models using AI and ML, combining fuzzy data, big data, small data, and tacit knowledge to create an institutional knowledge repository that interprets context and supports decision-making and predictions, leveraging a continuous feedback loop and human expertise.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If traditional data-driven decision-making methods are used, then quantitative analysis is performed, but qualitative and fuzzy data cannot be effectively integrated, leading to incomplete institutional knowledge

Engineering Contradiction:
Improvedata integration capabilityVSAvoidinstitutional knowledge reliability
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The patent merges quantitative data-driven methods with qualitative expert judgment systems into a unified hybrid framework. The system combines statistical models, machine learning algorithms, and fuzzy logic with human expert knowledge, allowing both quantitative and qualitative data types to be processed together to create comprehensive institutional knowledge.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent introduces an intermediary knowledge representation layer that translates both quantitative data and qualitative expert knowledge into a common computational format. This intermediary layer enables seamless integration of diverse data types while maintaining their respective strengths and interpretations.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Loss of information

If fuzzy data and tacit knowledge are incorporated, then institutional knowledge completeness is improved, but data processing complexity increases

Engineering Contradiction:
Improveinformation completenessVSAvoidprocessing system complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The patent segments the knowledge processing system into distinct modules: quantitative data processing, qualitative data processing, fuzzy logic reasoning, and knowledge integration. Each module handles specific data types and processing tasks independently, reducing overall system complexity while maintaining comprehensive information processing capability.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent transforms qualitative and fuzzy data into quantifiable parameters through standardized representation schemes. By converting tacit knowledge into structured data formats and assigning numerical values to fuzzy concepts, the system reduces processing complexity while preserving information completeness.

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If human expertise is integrated with AI algorithms, then decision-making quality is enhanced, but system implementation complexity increases

Engineering Contradiction:
Improveprediction accuracyVSAvoidsystem implementation complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent designs a universal knowledge representation framework that can accommodate both AI algorithms and human expert knowledge using the same data structures and processing mechanisms. This multi-functional approach allows the system to handle diverse knowledge sources uniformly, enhancing prediction accuracy without proportionally increasing implementation complexity.

Inventive Principle:
Principle #6Universality (Multi-functionality)

4Adaptability or versatility

If diverse data types are integrated, then predictive capabilities are improved, but data interpretation difficulty increases

Engineering Contradiction:
Improvepredictive capabilityVSAvoiddata interpretation difficulty
Core Design Contradiction:
Adaptability or versatilityVSDifficulty of detecting and measuring

Solution Approach 1:

The patent introduces an intermediary knowledge translation layer that automatically interprets and standardizes diverse data types into a unified representation. This intermediary layer handles the complexity of data interpretation transparently, allowing the system to maintain high predictive capability while presenting simplified, easily interpretable results.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP4703914A1Method for developing institutional knowledge to support institutional memory, decision-making, and predictive capabilities through advanced data integration and ai
Publication Date: 2026.03.04 ENTERTEQ SOFTWARE SRL
  • EP4703914A1 patent drawingFigure 1~2
  • EP4703914A1 patent drawingFigure 3~4
  • EP4703914A1 patent drawingFigure 5~6

AI summary

The invention refers to a method for integrating quantitative and qualitative predictive models using Al and machine learning to enhance institutional knowledge management. By combining static, dynamic, and fuzzy data with tacit knowledge, the method creates a comprehensive institutional knowledge repository that supports decision-making and prediction. The approach involves capturing diverse data, transforming it into a small data framework for contextual understanding, and incorporating tacit knowledge through human input. An inference database is then developed to integrate qualitative and quantitative models, refined through continuous feedback loops. Leveraging modern AI and ML technologies, the invention creates a hybrid model that enhances decision-making by blending expert knowledge and scenario analysis with statistical and machine learning techniques. The framework also defines requirements for accessing institutional memory and ensures continuous improvement through automated feedback mechanisms.