Fleet Behavior Rules Using Geofenced Mobility Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Operators of vehicle fleets face challenges in analyzing and modifying vehicle behavior in real-time due to the manual and non-digital nature of aggregated vehicle event data, particularly in large fleets, and lack access to data from other fleets, making it difficult to adjust behavior based on comprehensive insights.
Innovation Solution
A mobility management system acts as an intermediary between mobility operators and governing entities, processing data to identify geographic areas of interest and applying vehicle rules, generating behavior modifications, and modifying rules based on historical data using machine-learned models to predict vehicle behavior and adjust fees or restrictions dynamically.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual analysis of fleet vehicle event data is performed, then data processing can be done with simple tools, but the analysis time and effort increase significantly for large fleets
Solution Approach 1:
The patent introduces a mobility management system as an intermediary between governing entities and fleet operators. This system automatically ingests vehicle event data, geofences geographic areas, applies parking rules, and generates behavior modifications, eliminating the need for manual analysis of large volumes of fleet data while maintaining accurate compliance tracking.
Solution Approach 2:
The patent replaces manual mechanical analysis processes with automated computational systems. The mobility management system uses software-based geofencing, automated rule evaluation, and algorithmic behavior modification generation to substitute human manual data processing, dramatically increasing analysis speed and reducing time loss.
2Adaptability or versatility
If a mobility operator monitors only its own fleet data, then data privacy and security are maintained, but the operator cannot optimize behavior based on aggregated industry patterns
Solution Approach 1:
The mobility management system acts as a trusted intermediary that aggregates anonymized vehicle event data from multiple fleets and operators. It processes this aggregated data to identify behavioral patterns and generates optimized behavior modifications that can be applied individually by each operator, allowing benefit from collective data while maintaining individual data control.
Solution Approach 2:
The system creates anonymized copies of vehicle event data from multiple fleets for aggregated analysis. These copied datasets enable pattern recognition and behavior optimization without exposing sensitive proprietary information from any single operator, allowing each operator to benefit from industry-wide insights while maintaining data security.
3Reliability
If real-time vehicle behavior modification is implemented, then compliance with parking regulations improves, but the system complexity and computational requirements increase
Solution Approach 1:
The mobility management system performs preliminary actions by pre-defining geofences for geographic areas of interest and pre-configuring parking rules before vehicle events occur. When vehicle data is received, the system simply matches events against pre-established geofences and rules, significantly reducing real-time computational complexity while maintaining high compliance monitoring capability.
Solution Approach 2:
The system implements dynamic behavior modifications that adapt to real-time vehicle locations and events. Geofences and rules can be updated without system reconfiguration, and behavior modifications are dynamically generated based on current fleet positions and compliance patterns, allowing flexible real-time optimization without permanent system complexity increases.
Data Source
AI summary
Systems and methods are disclosed herein for a mobility management system that serves as a data processing intermediary between mobility operators and governing entities that define rules associated with vehicle behavior occurring in a geographic region. The system receives from a mobility operator historical vehicle data including GPS locations for fleet vehicles within the geographic region. The system determines aggregate behavior metrics for the vehicles using the behavior data. If the aggregate behavior metrics exceed one or more behavior thresholds for a specified time period, the system generates one or more suggested behavior modifications for the vehicles or mobility operators. Moreover, the historical vehicle data may be used to train a machine-learned model to predict a number and behavior of vehicles within the geographic region at a specific time, and if the current number or behavior of vehicles satisfies pre-determined governing criteria, the system modifies one or more vehicle rules.