Pattern Finding Device Reduces Similarity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing pattern finding devices often generate numerous patterns, including many similar ones, which can lead to inefficiencies and increased calculation time or memory usage.
Innovation Solution
A pattern finding device comprising a pattern generator, storage, selector, and deleter, which generates patterns, stores them, selects patterns to delete based on item distribution changes, and deletes similar patterns to reduce similarity, using evaluated values to maintain diversity and adhere to a maximum number of patterns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If pattern finding devices generate patterns based on frequency from sequence data sets, then patterns can be found, but many similar patterns are included in the results
Solution Approach 1:
The invention changes the evaluation parameter from simple frequency to a diversity-based metric that measures the distribution of items within patterns. By calculating the sum of squared frequencies of items in each pattern and using this as an evaluation value, the system identifies and removes patterns with poor item distribution (similar patterns), thereby maintaining pattern diversity while preserving productivity.
2Reliability
If all generated patterns are stored, then complete pattern set is available, but calculation time and memory usage increase excessively
Solution Approach 1:
The invention systematically discards redundant patterns by evaluating and removing patterns with poor item distribution (high similarity to other patterns). This selective discarding reduces the number of patterns that need to be stored and processed, thereby reducing calculation time and memory usage while maintaining the reliability of the remaining diverse patterns.
3Reliability
If all generated patterns are stored, then complete pattern set is available, but memory usage increases excessively
Solution Approach 1:
The invention reduces memory usage by discarding redundant patterns through evaluation based on item distribution. By removing patterns with high similarity (poor item distribution), the system maintains a compact set of diverse patterns that fits within acceptable memory constraints while preserving the essential information.
4Ease of operation
If pattern selection is based on frequency only, then simple selection process, but similar patterns are not eliminated
Solution Approach 1:
The invention enhances the selection process by introducing a new evaluation parameter based on item distribution (sum of squared frequencies) rather than relying solely on frequency. This parameter change enables the system to identify and eliminate similar patterns while maintaining relative simplicity in the selection mechanism.
Data Source
AI summary
A pattern finding device of embodiments includes a pattern generator, a pattern storage, a pattern selector, a pattern deleter. The pattern generator generates a group of patterns from data including a plurality of items. The pattern storage stores the group of patterns generated by the pattern generator. The pattern selector selects at least one pattern to be deleted from the group of patterns with reference to an evaluated value indicating a change of an item distribution condition in the group of patterns when at least one pattern which is selected as a candidate is excluded from the group of patterns stored in the pattern storage. The pattern deleter deletes the at least one pattern that is selected by the pattern selector from the pattern storage.