Route Selection Using Cognitive Rules
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current routing applications are limited in considering experiential knowledge and local conditions, often selecting routes that differ from those preferred by experienced drivers, as they primarily rely on shortest-distance methodologies without accounting for factors like traffic congestion, events, or weather.
Innovation Solution
A system that collects and applies cognitive route rules based on user input and historical data from experienced drivers, using a server-client architecture to integrate map data with route data, including condition flags and rules that adjust routing decisions based on time, weather, events, and other factors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If shortest-distance methodology is used for routing, then route calculation speed is improved, but route selection accuracy deteriorates
Solution Approach 1:
The routing system segments the route selection process into two distinct phases: first, a base route is calculated using fast shortest-distance methodology; second, cognitive route rules are applied to adjust the base route. This segmentation allows the system to maintain calculation speed while improving accuracy through experience-based adjustments.
Solution Approach 2:
The system performs preliminary action by collecting and storing cognitive route rules from experienced drivers before the actual routing decision is made. These pre-collected rules about traffic patterns, congestion, and local conditions are then applied to adjust the base route, improving accuracy without adding significant calculation time during the routing process.
2Measurement precision
If cognitive route rules from multiple sources are collected and applied, then route selection accuracy is improved, but system complexity increases
Solution Approach 1:
The server is designed with multi-functionality to handle multiple tasks: collecting cognitive route rules from various sources, storing them in a database, receiving routing requests, calculating base routes, and applying rule adjustments. This universal design consolidates complexity into a single multi-functional system rather than requiring separate specialized components for each function.
Solution Approach 2:
The server acts as an intermediary between experienced drivers (who provide route knowledge) and routing applications (which need route recommendations). The server collects, processes, and stores cognitive route rules, then applies them automatically when generating routes, mediating the complexity of knowledge collection and application between users and the routing system.
3Reliability
If routing applications consider more factors like traffic, events, and weather, then route quality is improved, but information requirements increase
Solution Approach 1:
Experienced drivers self-service by voluntarily providing their route knowledge and preferences to the system. Through the user interface, drivers input cognitive route rules about traffic patterns, congestion, and local conditions based on their own experience. This self-service approach collects valuable information without requiring the system to actively gather data from multiple external sources.
Solution Approach 2:
The system implements feedback by collecting actual driver routes and comparing them with recommended routes. This feedback loop allows the system to learn from the discrepancy between recommended and actual driver behavior, continuously improving the cognitive route rules and better understanding which factors (traffic, events, weather) most influence route selection in different geographic areas.
Data Source
AI summary
A request is received to compute a route from a start point to an end point. The route is computed using map data that includes a plurality of map elements, and route data that includes rules associated with the map elements, each of the rules being triggered by a condition flag that specifies a condition according to which the rule should be applied. The route data is based inputs related to driver experience in a geographic area associated with the route, and the inputs are based on stored data and not real-time or near-real-time data.