Regionality Score Calculation for Application Recommendation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing application recommendation systems fail to accurately estimate user interest in applications based on regionality, as they only consider routine vs. nonroutine areas, lacking detailed classification and recommendation.
Innovation Solution
A determination device that accumulates and analyzes user history information to calculate a regionality score for each application, considering both the frequency of use and number of regions where an application is used, to determine regionality and provide appropriate recommendations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If only classification into routine/nonroutine areas is performed, then the determination process is simple, but the accuracy of estimating user interest in applications for each region is insufficient
Solution Approach 1:
The patent segments the determination process into multiple distinct units: a history storage unit for accumulating use history information, a first totaling unit for calculating use tendency, a second totaling unit for counting regions, a score calculating unit for computing regionality scores, and a determination unit for final classification. This segmentation allows each unit to perform a specific function, improving measurement precision while managing complexity through modular design.
Solution Approach 2:
The patent transitions from a single-dimension classification (routine/nonroutine areas) to a multi-dimensional analysis by introducing multiple metrics: use tendency (frequency of application use), number of regions (spatial distribution), and regionality score (combined metric). This dimensional expansion enables more accurate estimation of user interest by considering both how often an application is used and where it is used.
2Measurement precision
If detailed classification of applications by regionality is implemented, then application recommendations become more accurate, but the computational load and data processing requirements increase
Solution Approach 1:
The patent applies partial action by focusing computational resources on calculating regionality scores only for applications that meet certain criteria. The determination unit identifies applications with significant regionality characteristics (those with notable differences in use patterns across regions) rather than performing exhaustive analysis on all applications, thereby reducing computational load while maintaining classification accuracy for the most relevant cases.
Solution Approach 2:
The patent transforms raw use history data into derived parameters (use tendency, number of regions, regionality score) that condense complex information into manageable metrics. By changing the form of data representation from detailed usage logs to aggregated statistical parameters, the system reduces computational requirements while preserving the essential information needed for accurate classification.
Data Source
AI summary
A determination device 1 includes: a history storage unit 101 configured to accumulate and store use history information in which application identification information, position information indicating a position of a user, and user identification information are correlated with each other; a use region UU number totaling unit 105 configured to total a UU number for each of a plurality of regions on the basis of the use history information for a specific application; a use region number totaling unit 106 configured to total the number of regions on the basis of the use history information for the specific application; a score calculating unit 107 configured to calculate a regionality score for each of the plurality of regions on the basis of the UU number and the number of regions for the specific application; and a determination unit 108 configured to determine whether there is regionality for the specific application on the basis of the regionality score.