Vector Mapping for Cross-DataSet Feature Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Data analysis is limited to the vector space of the original data set and cannot be extended beyond its range, leading to diluted feature representation when combining data sets, making it difficult to fully utilize the features of the vector spaces.
Innovation Solution
Forming separate vector spaces for each data set and mapping non-synonymous feature vectors from one space to another, allowing data analysis to be performed on a wider range of data sets while maintaining the features of the original spaces.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If data sets are combined to expand analysis coverage, then the range of data analysis is extended, but the feature representation becomes diluted and original vector space features are lost
Solution Approach 1:
The patent segments the data analysis process by maintaining separate vector spaces for different data sets. Each data set retains its own vector space with unique feature representations, preventing feature dilution while still enabling cross-data-set analysis through selective vector mapping between spaces.
2Measurement precision
If feature vectors are computed from a single data set, then the vector space maintains consistent feature representation, but data analysis is limited to that data set's range
Solution Approach 1:
The patent introduces vector mapping as an intermediary mechanism between separate vector spaces. This mapping enables the transfer and comparison of feature vectors across different data sets while preserving the unique feature representations of each space, thus extending analysis range without sacrificing feature consistency.
3Measurement precision
If separate vector spaces are maintained for each data set, then original feature representations are preserved, but the complexity of the system increases
Solution Approach 1:
The patent combines multiple separate vector spaces into a unified analysis framework through vector mapping. While maintaining distinct feature representations, the system integrates these spaces by mapping vectors between them, enabling comprehensive analysis without managing completely separate systems for each data set.
Data Source
AI summary
Vector computation units 1 and 2 for forming first and second vector spaces by computing a plurality of feature vectors from each of a first data set and a second data set, and a vector mapping unit 3 for mapping a feature vector not synonymous with a feature vector in the second vector space from the first vector space to the second vector space are included. Further, by mapping a feature vector not synonymous with a plurality of feature vectors included in the second vector space from the first vector space to the second vector space without changing the plurality of feature vectors, data analysis can be performed on, as targets, a feature vector originally included in the second vector space and a feature vector added from the first vector space.