Knowledge System Query Splitting for Decision-Making Relevance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional knowledge management systems are inadequate in providing relevant knowledge due to reliance on human-derived queries that do not consider contextual and conceptual parameters, often resulting in irrelevant information.
Innovation Solution
A knowledge system comprising a processor and memory with a knowledge access module and processing module that generates structured queries based on user requests, splits them by domain and metadata, fetches relevant knowledge objects from a database using ontologies, and integrates them to create a knowledge object for decision-making processes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional knowledge management systems rely on human-derived queries, then the system is simple to operate, but the relevance and accuracy of retrieved knowledge deteriorates due to lack of contextual and conceptual parameters
Solution Approach 1:
The patent introduces an intermediary layer (knowledge graph with ontologies and contextual parameters) between the user query and the knowledge database. This intermediary automatically enriches simple user queries with contextual and conceptual parameters, thereby improving knowledge relevance without requiring the user to understand complex system structures. The intermediary translates human-derived queries into sophisticated search operations automatically.
Solution Approach 2:
The system performs self-service by automatically generating and executing complex search operations based on simple user inputs. The knowledge management system autonomously enriches queries with contextual parameters, navigates the knowledge graph, and retrieves relevant information without requiring user expertise in system complexity. This allows the system to maintain simplicity of operation while achieving high measurement precision.
2Quantity of substance
If the system retrieves vast amount of electronically accessible knowledge, then the quantity of available information increases, but the quality and relevance of provided knowledge deteriorates
Solution Approach 1:
The patent applies local quality by differentiating between various types of knowledge parameters (contextual, conceptual, factual) and retrieving only the specific local qualities needed for each query. Instead of retrieving all available knowledge uniformly, the system selectively accesses relevant portions of the knowledge base by matching query parameters with corresponding knowledge graph nodes and edges, thereby maintaining high relevance while accessing vast knowledge quantities.
Solution Approach 2:
The system dynamically changes parameters during the knowledge retrieval process by adapting search criteria based on the specific query, contextual parameters, and knowledge graph structure. The system transforms the static vast knowledge base into dynamic relevant results by adjusting retrieval parameters in real-time, ensuring that the quantity of accessed knowledge matches the specific informational needs of each query rather than retrieving all available data.
3Productivity
If the system uses human-derived queries without contextual parameters, then the ease of operation is maintained, but the productivity of knowledge retrieval deteriorates
Solution Approach 1:
The system performs self-service by automatically executing complex multi-step retrieval operations based on simple user inputs. When a user submits a basic query, the system autonomously enriches it with contextual parameters, navigates the knowledge graph structure, and retrieves relevant information without requiring the user to understand or specify these complex operations. This maintains ease of operation while dramatically improving retrieval productivity.
Solution Approach 2:
The system performs preliminary actions by pre-processing and structuring knowledge into a knowledge graph with ontologies and contextual parameters before retrieval occurs. This preliminary organization enables rapid and efficient querying, as the system has already prepared the knowledge structure in advance. Users benefit from this pre-prepared structure by simply submitting queries without needing to perform complex retrieval operations themselves.
Data Source
AI summary
Disclosed is a knowledge system for retrieving a knowledge object, pertaining to a query, in a cognitive decision-making process. The knowledge system comprises a knowledge access module and a knowledge processing module. The knowledge access module may receive a knowledge request requesting a knowledge object. In one aspect, the knowledge request may be associated to at least one domain. The knowledge access further generates a structured query based on the knowledge request. The knowledge access module further splits the structured query into one or more sub queries. In one aspect, the structured query may be split based on the at least one domain and metadata associated to the at least one domain. The knowledge access module further fetches one or more knowledge objects for each sub query upon executing the one or more sub queries on a system database storing a plurality of knowledge objects. In one aspect, the one or more knowledge objects may be fetched upon referring to one or more ontologies stored in the system database. The knowledge processing module creates and thereby stores an integrated knowledge object for the knowledge request upon integrating the one or more knowledge objects fetched by the one or more sub queries.