Velocity Recommendation via Location Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing driving support systems fail to provide effective real-time velocity recommendations and alerts based on location-specific driving habits, leading to potential safety risks due to inadequate analysis of movement data and visual/audible signals.
Innovation Solution
A method and system that generate and update a commonly driven velocity dataset using location and bearing data from client devices, processing this data to provide real-time recommended velocities and alerts through audio, visual, or vibration notifications when the current velocity deviates from the recommended range.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If real-time velocity monitoring and analysis is implemented, then driving safety is improved, but system complexity and data processing requirements increase
Solution Approach 1:
The system segments the dataset into multiple location points along the route, with each location point having its own commonly driven velocity calculation. This allows distributed processing of velocity data across different locations, reducing the complexity burden on any single processing component while maintaining comprehensive safety monitoring.
Solution Approach 2:
The patent introduces an intermediary processing layer that collects velocity data from multiple client devices, calculates commonly driven velocities for each location point, and provides recommendations back to drivers. This intermediary layer abstracts the complex data processing from individual devices, enabling safety improvements without requiring each device to handle the full computational burden.
2Reliability
If location-specific velocity recommendations are provided, then traffic safety is improved, but data collection and processing requirements increase
Solution Approach 1:
The system merges velocity data from multiple client devices traveling along the same or similar routes to build a comprehensive dataset. By combining data from multiple sources, the system achieves more accurate commonly driven velocity calculations for each location point without requiring each individual device to collect excessive data independently.
Solution Approach 2:
The collected velocity data serves multiple functions: it is used to calculate commonly driven velocities, generate safety recommendations, update datasets for future comparisons, and provide statistical analysis. This multi-functionality maximizes the value extracted from the collected data, reducing the need for continuous extensive data collection while maintaining safety improvements.
3Measurement precision
If commonly driven velocity dataset is continuously updated, then recommendation accuracy is improved, but processing time and computational load increase
Solution Approach 1:
The system performs preliminary calculations by pre-processing velocity data and storing commonly driven velocities for multiple location points in advance. When a driver reaches a specific location, the system can quickly retrieve and compare the pre-calculated commonly driven velocity without performing complex real-time analysis, thus maintaining high recommendation accuracy while minimizing processing time.
Solution Approach 2:
The dataset is dynamically updated by incorporating new velocity data from client devices while maintaining historical data. The system adapts the commonly driven velocity calculations based on accumulated data, improving recommendation accuracy over time. The dynamic nature allows the system to balance between using historical data for stability and incorporating new data for accuracy improvements without requiring complete re-processing.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method of calculating a commonly driven velocity recommendation, comprising: gathering a plurality of data messages from a plurality of client devices located in a plurality of different vehicles, each data message comprises a current location value, a current bearing value, and a current velocity value estimated for a hosting vehicle; clustering the plurality of data messages in a plurality of clusters by matching the respective location values and bearing values; calculating a commonly driven velocity per cluster of the plurality of clusters by combining data from respective cluster members; and retrieving the commonly driven velocity in response to an indication of a current location and a current bearing thereof which matches location and bearing of members of the respective cluster.