Intelligent Ad-Based Routing for Ride-Sharing Cost Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods of electronic advertisement delivery do not consider physical advertisement locations along a driving route, resulting in generic and non-targeted advertisements that are inefficient and costly for both users and businesses.
Innovation Solution
The system creates intelligent ad-based routes by aggregating user profile data, destination characteristics, and real-time business data to select relevant advertisements and route passengers through physical advertisement locations, allowing businesses to offset ride-sharing costs by displaying targeted ads during the ride.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If the system takes a longer route to increase advertisement exposure, then the ride cost decreases for users, but the travel time increases
Solution Approach 1:
The system dynamically adjusts the route based on real-time factors including user preferences, advertisement budget, and cost parameters. The routing algorithm continuously optimizes the path to balance travel time against advertisement exposure value, allowing the route to adapt between direct (fastest) and detour (more ads) options based on dynamic conditions.
Solution Approach 2:
The system changes the routing parameters by introducing advertisement exposure as a new dimension in route optimization. Instead of solely minimizing travel time or distance, the system incorporates ad value metrics and cost parameters to create a multi-parameter optimization model that balances time, cost, and advertisement exposure.
2Device complexity
If the system delivers generic advertisements without considering physical advertisement locations, then the advertisement delivery is simpler, but the relevance and efficiency of advertisements decrease
Solution Approach 1:
The system performs preliminary actions by pre-mapping physical advertisement locations along potential routes before actual delivery. It aggregates location data, business information, and user profile data in advance to create a prepared advertisement delivery plan that matches users with relevant ads based on their route and preferences.
Solution Approach 2:
The system introduces an intermediary layer that acts as a matchmaker between physical advertisement locations and users. This intermediary processes user profiles, destination characteristics, and ad location data to selectively deliver relevant advertisements, rather than broadcasting generic ads to all users.
3Reliability
If the system uses machine-learning classification algorithms to select relevant advertisements, then the advertisement relevance increases, but the processing time and computational resources increase
Solution Approach 1:
The system performs preliminary classification and filtering of advertisements based on user profiles and destination characteristics before the actual ride. By pre-processing and categorizing relevant ads in advance, the system reduces the computational burden during real-time route planning and advertisement delivery.
Solution Approach 2:
The system applies partial classification by focusing machine-learning algorithms on key discriminating features rather than analyzing all possible advertisement attributes. It selectively processes the most relevant user profile elements and ad characteristics to achieve sufficient relevance without exhaustive computation.
Data Source
AI summary
Examples of the present disclosure describe systems and methods for intelligent ad-based routing. In example aspects, a destination input, desired time for arrival, and user profile data is received in a ride-sharing application. The input data is classified by applying one or more machine-learning models to the data. Based on the classified data results, candidate physical advertisement locations may be selected along a certain route. Different types of routes may be selected that range from the shortest possible route (i.e., a direct route) to a major detour (i.e., the most cost-effective route). A major detour takes the user on a route that exposes the user to as many advertisements as possible while still arriving at the final destination before the desired time of arrival. In exchange for a longer route and more exposure to physical advertisements, the cost of the ride may be offset.