Feature Classification and Ranking Strategy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Analyzing datasets with a large number of features is challenging due to the difficulty in classifying and ranking features effectively, as existing dictionary-based semantic classification methods often leave a significant portion of features unclassified.
Innovation Solution
A classification and ranking strategy that assigns hierarchical and semantic ranks to features based on their schema level and semantic context, using a hierarchical schema and a semantic model with entity, events, and actions semantic levels, allowing features to be grouped into categories based on their computed rank.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If dictionary-based semantic classification is used to classify features, then classification speed is improved, but classification completeness deteriorates (resulting in unclassified features)
Solution Approach 1:
The patent introduces a semantic similarity computation mechanism as an intermediary between the dictionary lookup and final classification. When dictionary lookup fails to classify a feature, the system computes semantic similarity between the feature and existing classified features using a semantic model, allowing features to be classified based on their semantic relationship to known features rather than requiring exact dictionary matches
Solution Approach 2:
The system performs preliminary dictionary-based classification to quickly classify features with exact matches, then applies semantic similarity computation only to the remaining unclassified features. This two-stage approach maintains high overall classification speed while ensuring complete classification of all features
2Productivity
If hierarchical schema and semantic model are used to compute feature ranks, then feature analysis efficiency is improved, but computational complexity increases
Solution Approach 1:
The patent segments the feature ranking process into distinct components: hierarchical schema-based ranking, semantic model-based ranking, and combined ranking. Each component operates independently and can be computed separately, allowing for modular implementation and optimization of each segment without increasing overall system complexity
Solution Approach 2:
The system changes the parameter space by introducing hierarchical levels and semantic contexts as additional dimensions for feature ranking. Instead of ranking features based on a single criterion, the patent uses multiple parameters (hierarchical position, semantic similarity) that can be weighted and combined to produce comprehensive feature rankings
Data Source
AI summary
Systems and methods provide for classification and ranking of features for a hierarchical dataset. A hierarchical schema of features from the dataset is accessed. A hierarchical rank is assigned to each feature based on its schema level in the hierarchical schema. Additionally, a semantic rank is assigned to each feature using a semantic model having ranked semantic contexts. The semantic rank of a feature is assigned by identifying a semantic context of the feature and assigning the rank of the semantic context as the semantic rank of the feature. A rank is computed for each feature as a function of its hierarchical rank and semantic rank.