Adaptive Spatial Density Clustering for Habitual Place Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional density-based clustering algorithms struggle to accurately identify habitual places of users due to the need for a fixed density threshold, which becomes ineffective as the number of visit points increases and positioning inaccuracies occur.
Innovation Solution
The proposed solution dynamically adjusts the density threshold of the clustering algorithm by increasing it when the number of visit points in a cluster exceeds a maximum cluster size, allowing for more accurate identification of habitual places.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If a fixed density threshold is used in conventional density-based clustering algorithms, then the algorithm is simple to implement, but it becomes ineffective as the number of visit points increases and positioning inaccuracies occur
Solution Approach 1:
The patent applies the dynamics principle by transforming the fixed density threshold into a dynamic parameter that adapts to changing data conditions. The system automatically adjusts the density threshold based on the distribution characteristics of visit points, ensuring reliable clustering results even as the number of visit points increases or positioning inaccuracies occur.
Solution Approach 2:
The patent implements parameter changes by modifying the density threshold parameter during the clustering process. Instead of using a predetermined fixed value, the system changes the density threshold parameter dynamically based on the actual data distribution, thereby maintaining high clustering accuracy under varying conditions.
2Quantity of substance
If the number of visit points increases, then more comprehensive location data is available, but conventional clustering algorithms with fixed density thresholds become less effective at identifying habitual places
Solution Approach 1:
The system dynamically adjusts the density threshold based on the quantity of visit points. As more visit points are accumulated, the algorithm adapts the density parameter to maintain appropriate clustering granularity, preventing the merging of distinct habitual places into a single cluster.
Solution Approach 2:
The patent employs feedback mechanisms where the clustering results are evaluated and used to adjust the density threshold for subsequent clustering operations. This iterative feedback process ensures that as more visit points are added, the system learns from previous clustering outcomes and refines its parameters to maintain high identification accuracy.
3Reliability
If positioning inaccuracies occur, then real-world location data is captured, but fixed density threshold clustering fails to accurately identify habitual places
Solution Approach 1:
The system responds to positioning inaccuracies by dynamically changing the density threshold parameter. When location data with inherent inaccuracies is processed, the algorithm adjusts the density parameter to accommodate the variability, ensuring that habitual places are still accurately identified despite the noise in the input data.
Solution Approach 2:
The patent applies beforehand cushioning by incorporating robustness into the clustering algorithm design. The dynamic parameter adjustment mechanism acts as a buffer against positioning inaccuracies, allowing the system to maintain reliable clustering performance even when input location data contains errors or variations.
Data Source
AI summary
Methods, systems, and devices for identifying the habitual places of a user, the habitual places of a user being the places where the user spends most of his/her time. In some embodiments, historical location information of a user is accessed, and a plurality of visit points are identified based on the historical location information. The plurality of visit points is clustered into a plurality of clusters. Each one of the clusters is then associated with a habitual place of the user. When the server receives, from a client device associated with the user, current location information of the user, the server identifies a current location of the user based on the current location information, and, if the current location of the user is in a neighborhood of one of the clusters, determine that the user is at the habitual place associated with the cluster.