Action Pattern Analysis Device for Irregular Position Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing action pattern analysis devices struggle to accurately manage user actions when position information is measured at longer intervals or irregularly, leading to reduced accuracy in analyzing daily patterns and movement paths.
Innovation Solution
An action pattern analysis device that plots position information logs in a multidimensional space, weights the data to determine Euclidean distances, and clusters stay points and moving paths, allowing for accurate extraction of frequent stay locations and movement routes even with irregular data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If position information is measured at longer time intervals to protect user privacy, then user privacy is protected, but the accuracy of action pattern analysis deteriorates
Solution Approach 1:
The patent transforms the one-dimensional time-series position data into a two-dimensional clustering space by introducing a weighting mechanism. Position information logs are plotted in a clustering space where the Euclidean distance calculation incorporates time-based weighting, allowing the system to distinguish between stay points (short weighted distance) and moving paths (long weighted distance) even with irregular measurement intervals.
Solution Approach 2:
The patent changes the parameter of distance calculation by introducing a weighting factor based on time intervals. The Euclidean distance in the clustering space is calculated as the square root of the sum of squared differences in position coordinates, where the time dimension is weighted to reflect the temporal characteristics of user behavior. This parameter change enables accurate pattern recognition despite irregular sampling intervals.
2Quantity of substance
If position information is measured at longer time intervals to reduce data storage requirements, then data storage requirements are reduced, but the accuracy of extracting stay points and moving paths deteriorates
Solution Approach 1:
The patent plots position information logs in a clustering space that combines spatial coordinates with time-based weighting. This dimensional transformation allows the system to capture the temporal patterns of user behavior in the spatial distribution of data points, enabling accurate extraction of stay points and moving paths even when data is sparsely sampled over time.
Solution Approach 2:
The patent modifies the distance calculation parameter by incorporating time interval weighting into the Euclidean distance formula. This parameter change allows the clustering algorithm to differentiate between points that are close in space but far in time (moving paths) versus points that are close in both space and time (stay points), maintaining extraction accuracy with reduced data volume.
3Adaptability or versatility
If position information is irregularly measured to balance privacy and service quality, then user privacy is protected and service quality is maintained, but the accuracy of action pattern analysis deteriorates
Solution Approach 1:
The patent applies a dynamic weighting mechanism to the time intervals between position measurements. The weighting factor is adjusted based on the actual time difference between consecutive measurements, allowing the system to adapt to irregular sampling patterns. This dynamic parameter adjustment enables the clustering algorithm to correctly interpret the temporal relationships in irregularly sampled data.
Solution Approach 2:
The patent changes the calculation parameters by introducing time-based weighting into the Euclidean distance formula. This parameter modification allows the system to process irregularly measured position information effectively, as the weighting compensates for variable time intervals between measurements, maintaining analysis accuracy while preserving user privacy through reduced measurement frequency.
Data Source
AI summary
A position information plot means 81 plots a position information log containing a user's measurement position and measurement date/time on a multidimensional space defined by numerical information indicating the measurement position and a time. A slay point cluster extraction means 82 weights the position information log so that a Euclidean distance in a time direction relative to a position information space is easily determined as short, and clusters the weighted position information logs thereby to extract a stay point where the user frequently stays. A moving path cluster extraction means 84 weights a position information log at a non-stay point so that a Euclidean distance in a time direction relative to a position information space is easily determined as long, and clusters the weighted position information logs thereby to extract a user's moving path.