Neural Network Ride Dispatching for Driver Earnings
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current ride order dispatching systems fail to maximize earnings for vehicle drivers, as they rely on personal experiences or random decisions, leading to suboptimal allocation of transportation requests.
Innovation Solution
A ride order dispatching system utilizing a trained neural network model, combining deep neural networks and reinforcement learning algorithms, to determine optimal actions such as staying, repositioning, or accepting ride orders based on current location and time, thereby maximizing cumulative rewards.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If ride order dispatching relies on personal experiences or random decisions, then the system is simple to operate, but earnings for vehicle drivers are not maximized
Solution Approach 1:
The system enables drivers to automatically receive optimized dispatching decisions through the neural network model without requiring manual analysis or complex decision-making processes. The model autonomously processes driver location, time, and historical data to generate actionable recommendations, making the sophisticated algorithm as easy to use as simple random selection while dramatically improving earnings
Solution Approach 2:
The patent replaces the mechanical decision-making process (human judgment based on experience) with an intelligent system based on neural networks and reinforcement learning. This substitution transforms subjective, inconsistent human decisions into objective, data-driven recommendations that maximize driver earnings while maintaining ease of operation through automated delivery of decisions
2Productivity
If a neural network model with deep-Q networks and reinforcement learning is used, then driver earnings are maximized, but the system complexity increases
Solution Approach 1:
The neural network model is trained offline using historical ride order data and reinforcement learning algorithms before deployment. This preliminary training phase allows the complex model to learn optimal dispatching strategies in advance, so that during actual operation, the system only needs to query pre-computed recommendations rather than performing complex real-time calculations, thereby reducing operational complexity while maintaining high earnings
Solution Approach 2:
The patent introduces a recommendation system as an intermediary between the complex neural network model and the driver. This intermediary layer translates complex model outputs into simple, actionable recommendations that drivers can easily follow, effectively shielding users from the underlying system complexity while still benefiting from the advanced algorithms' earnings-maximizing capabilities
Data Source
AI summary
A ride order dispatching system comprises a processor, and a non-transitory computer-readable storage medium storing instructions that, when executed by the processor, cause the processor to perform a method. The method comprises: obtaining, from a computing device, a current location of a vehicle; inputting the current location of the vehicle and a time to a trained neural network model to obtain action information for the vehicle, the action information comprising: staying at the current location of the vehicle, re-positioning the vehicle, or accepting a ride order; and transmitting the action information to the computing device to cause the vehicle to stay at the current location, re-position to another location, or accept the ride order by proceeding to a pick-up location of the ride order.