Score Calculation Unit for Sensor Data Catalog Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In sensor network systems, the arbitrary selection of words for observation objects and characteristics in metadata catalogs by providers and users can lead to inaccurate matching, preventing appropriate judgment of data catalog coincidence and hindering the provision of desired sensing data.
Innovation Solution
A score calculation unit is introduced, comprising weight determination parts and a score calculation part, which calculates a score based on the association between words in metadata catalogs, using techniques like synonyms and hypernyms to assess the coincidence of observation objects and characteristics, even when expressed differently.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If arbitrary words are selected for observation objects and characteristics in metadata catalogs by providers and users, then the ease of creating metadata is improved, but the accuracy of matching between sensor-side and application-side metadata deteriorates
Solution Approach 1:
The patent introduces a scoring mechanism that acts as an intermediary between arbitrary metadata terms. Instead of direct binary matching, the system calculates coincidence scores based on multiple factors including word frequency, co-occurrence relationships, and semantic associations. This intermediary scoring system bridges the gap between freely chosen terms and accurate matching requirements.
Solution Approach 2:
The patent transforms the matching problem from a binary coincidence judgment to a multi-parameter scoring evaluation. It changes the assessment parameters to include word frequency in catalogs, co-occurrence frequencies with other terms, and similarity scores with reference terminology. This parameter transformation allows flexible matching while maintaining accuracy.
2Measurement precision
If exact word matching is used to judge coincidence of data catalogs, then the precision of matching judgment is improved, but the adaptability to different terminology selections deteriorates
Solution Approach 1:
The patent implements a dynamic matching system where the coincidence score is not fixed but adapts based on the specific terms involved. The scoring mechanism dynamically adjusts weights and considerations based on word frequency, catalog-specific usage patterns, and contextual co-occurrences. This dynamic approach maintains precision while adapting to various terminology choices.
Solution Approach 2:
The patent creates a universal scoring framework that can handle multiple terminology styles and domains. The same matching mechanism works across different sensor types, application domains, and metadata vocabularies by using relative frequency and co-occurrence statistics rather than domain-specific rules, making it universally applicable while maintaining precision.
3Speed
If simple coincidence judgment is used for metadata matching, then the processing speed is improved, but the accuracy of determining data provision capability deteriorates
Solution Approach 1:
The patent performs preliminary actions by pre-calculating and storing word frequency statistics, co-occurrence matrices, and reference terminology databases during system initialization or offline processing. This preliminary preparation allows the actual matching process to proceed quickly by retrieving pre-computed values rather than performing complex analyses in real-time, thus maintaining both speed and accuracy.
Data Source
AI summary
First and second data catalogs each indicate sensing data attributes. The first and second data catalogs each include a first word indicating an observation object of a sensor that generated sensing data and a second word indicating an observation characteristic of the sensor. A score calculation unit includes a first weight determination part, a second weight determination part, and a score calculation part. The first weight determination part determines a first weight value relating to the observation object, based on the relationship between the first words included in the first and second data catalogs. The second weight determination part determines a second weight value relating to the observation characteristic, based on the relationship between the second words included in the first and second data catalogs. The score calculation part calculates a score relating to the coincidence of the first and second data catalogs, using the first and second weight values.


