Hybrid Knowledge Framework for Objective Assessment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current assessment models fail to account for context and causal relationships between intrinsic characteristics of an assessment object and its environmental context, leading to subjective and unreliable determinations due to lack of semantic integration and objective evidence-based scoring.
Innovation Solution
A computer-implemented system that uses a hybrid knowledge framework combining ontologies, generative AI, and machine learning to create a semantic and logical assessment theory model, enabling the identification of causal relationships and objective scoring through weighted scoring based on importance, trustworthiness, and certainty factors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If current assessment models are used, then simplicity and ease of operation are maintained, but measurement precision and reliability deteriorate due to lack of semantic integration and context awareness
Solution Approach 1:
The patent segments the assessment model into distinct modules: a knowledge framework module that stores semantic relationships and context information, an assessment module that processes evaluation data, and an integration module that combines them. This segmentation allows the system to achieve high measurement precision through semantic integration while managing complexity through modular architecture.
Solution Approach 2:
The patent introduces a knowledge framework as an intermediary layer between raw assessment data and evaluation outcomes. This framework contains ontologies, semantic relationships, and context information that mediate the assessment process, enabling accurate context-aware evaluations without requiring the entire system to be overly complex.
2Reliability
If expert-based subjective assessments are used, then ease of operation is maintained, but reliability and objectivity worsen due to lack of evidence-based scoring
Solution Approach 1:
The patent implements feedback mechanisms where assessment results are continuously refined based on evidence quality, semantic consistency, and context alignment. The system provides feedback loops that adjust scoring based on the strength of evidence and the degree of semantic integration, thereby improving reliability while maintaining operational clarity through automated feedback processing.
Solution Approach 2:
The patent replaces manual expert judgment mechanisms with an automated assessment system that uses machine learning models, semantic analysis algorithms, and evidence-based scoring mechanisms. This substitution transforms subjective expert assessments into objective, reproducible evaluations while reducing operational complexity through automation.
3Adaptability or versatility
If static large language models are used, then device complexity is reduced, but adaptability worsens due to inability to evolve over time
Solution Approach 1:
The patent transforms static large language models into dynamic systems that continuously evolve through integration with assessment data, feedback loops, and knowledge framework updates. The model adapts its parameters and structures based on accumulated assessment experiences and semantic relationships, enabling continuous improvement while managing architectural complexity through incremental evolution strategies.
Solution Approach 2:
The patent enables the assessment system to self-improve by automatically integrating new assessment data, updating the knowledge framework, and refining model parameters without requiring complete external reconfiguration. The system performs self-updates and adaptive learning, reducing the operational complexity of maintaining adaptability while continuously improving assessment capabilities.
Data Source
AI summary
A computer-implemented system, a method, and computer products for development and use of a knowledge framework are provided. The system comprises one or more processors and a memory including computer program code. The computer program code is configured to, when executed, cause the one or more processors to perform various tasks. These tasks include receive session data related to responses received from a participant in a session, receive machine learning data, create or enhance the knowledge framework based on the machine learning data and the session data, and create additional machine learning data using the knowledge framework as a source of information. The method performs these tasks, and the computer readable medium contains similar computer program code. The method can perform these tasks with computer synergistic generative artificial intelligence, machine learning, and knowledge framework subsystems.