Iterative Analysis Method Selection for Time-Series Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data analysis methods lack a mechanism to effectively present and select appropriate analysis methods to users when no prior knowledge is available, leading to ineffective user feedback and suboptimal analysis results.
Innovation Solution
A data analysis method selection device and program that evaluates relationships between time-series data using multiple analysis methods, extracts combinations with different trends, classifies methods based on evaluation values, presents data to users for similarity feedback, and iteratively scores and selects the most suitable analysis method.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If multiple analysis methods are applied to time-series data, then analysis comprehensiveness is improved, but user selection difficulty increases
Solution Approach 1:
The system implements an iterative feedback mechanism where users provide feedback on displayed time-series data combinations, and the system uses this feedback to adjust and refine the selection of analysis methods. The feedback unit receives user input about which combinations are more similar, and the scoring unit updates analysis method scores accordingly, creating a closed-loop system that adapts to user preferences.
Solution Approach 2:
The system dynamically changes the parameters of analysis method selection by adjusting scores based on user feedback. The scoring unit modifies the evaluation values of analysis methods according to user responses, transforming static analysis results into dynamic, user-adapted selections. This parameter adjustment enables the system to pivot between different analysis methods based on real-time user input.
2Ease of operation
If analysis methods are automatically selected, then operation simplicity is improved, but analysis accuracy decreases
Solution Approach 1:
The system balances automatic operation with accuracy by implementing feedback loops that continuously refine analysis selections. Users provide feedback on displayed data combinations, and the system automatically adjusts analysis method scores based on this feedback, ensuring that automated selections become increasingly accurate over time while maintaining operational simplicity.
Solution Approach 2:
The system performs preliminary actions by pre-calculating and displaying multiple time-series data combinations before final selection. The combination extraction unit prepares and presents multiple potential analysis combinations in advance, allowing users to review and provide feedback on preliminary selections, which then guide the final accurate analysis method selection.
3Reliability
If user feedback is collected, then analysis relevance is improved, but system complexity increases
Solution Approach 1:
The system segments the feedback collection process into discrete, manageable components. The inquiry unit presents specific time-series data combinations to users in an organized manner, and the feedback unit captures user responses as discrete inputs. This segmentation of the feedback mechanism reduces the perceived complexity while maintaining the ability to collect relevant user feedback for improving analysis relevance.
4Ease of operation
If multiple time-series data combinations are presented, then user feedback effectiveness is improved, but information overload increases
Solution Approach 1:
The system applies partial action by presenting a selected subset of time-series data combinations to users rather than all possible combinations. The combination extraction unit identifies and displays the most relevant combinations based on evaluation values, providing enough information for effective user feedback without overwhelming the user with excessive data. This partial presentation strategy maintains feedback effectiveness while managing information load.
Data Source
AI summary
A device includes: a data set including multiple sets in which two pieces of time-series data are respectively recorded; an analysis unit that obtains evaluation values representing a relationship between the two pieces by different analysis methods for each set; a combination extraction unit that extracts combinations of the sets having different trends in change in the evaluation values associated with the analysis methods; a grouping unit that classifies the analysis methods according to the evaluation values for each combination, and records results associated with the sets; an inquiry unit that presents the time-series data of each set to a user, and inquires which sets have similar time-series data; a scoring unit that adds a score of the analysis method belonging to the group having a better evaluation value for the set determined to be more similar; and a selection unit that repeats each process and selects an analysis method.