Transport Demand Forecasting Heatmaps for Driver-Specific Booking Probability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems fail to provide driver-specific, real-time data on the likelihood of receiving a booking, leading to inefficient taxi allocation and increased traffic, noise, and safety risks due to incomplete knowledge of demand and vehicle capacity.
Innovation Solution
A communications server apparatus that generates driver-specific, spatio-temporal heatmap data by aggregating and processing supply and demand data, using supply pooling logic to group drivers by vehicle type, and updating models in real-time to provide accurate probability forecasts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If general area-based taxi demand information is provided to all drivers, then drivers receive comprehensive information about potential fares, but the information becomes extraneous and irrelevant to individual drivers based on their location and vehicle type
Solution Approach 1:
The patent segments the general demand information into driver-specific heatmaps by filtering and personalizing data based on each driver's vehicle type, current location, and service capabilities. This segmentation transforms comprehensive but generic information into targeted, actionable intelligence for each driver without losing underlying demand patterns.
Solution Approach 2:
The system applies local quality by customizing the information presented to each driver according to their specific characteristics - vehicle type, location, and service pool assignments. Each driver receives a personalized heatmap that highlights only the areas and fare types relevant to their capabilities, making the information locally optimized for their operational context.
2Ease of operation
If detailed, driver-specific heatmap data is generated for each driver, then information relevance and usability improve, but processing overhead and system complexity increase
Solution Approach 1:
The system performs preliminary action by pre-computing heatmaps for different vehicle types and geographic regions offline or in advance. These pre-computed heatmaps are stored and then quickly retrieved and presented to drivers in real-time, avoiding the need to generate personalized data from scratch for each driver-query interaction.
Solution Approach 2:
The patent merges the personalization logic with the heatmap generation process by integrating driver profile data (vehicle type, location, service pool) directly into the heatmap computation pipeline. This merging allows the system to generate personalized heatmaps efficiently by combining pre-computed regional demand data with driver-specific filters in a unified processing step.
3Reliability
If real-time updates of heatmap data are provided to drivers, then the information remains valid and useful, but processing overhead and computational requirements increase
Solution Approach 1:
The system implements periodic action by updating driver heatmaps at regular intervals (e.g., every 15-30 seconds) rather than continuously in real-time. This periodic update approach maintains information validity while significantly reducing processing overhead compared to continuous real-time updates, as the system only needs to recompute heatmaps at scheduled intervals rather than responding to every data change immediately.
Data Source
AI summary
A communications server apparatus for simulating supply and demand conditions related to a transport service and deriving associated spatio-temporal prediction data, the communications server apparatus comprising a processor and a memory, and being configured, under the control of the processor, to execute instructions stored in the memory to: obtain supply and demand data, said supply data comprising service provider location and availability data and said demand data comprising user bookings data; generate, using said supply and demand data, aggregated supply and demand data comprising a plurality of data records associated with a plurality of respective predetermined time periods, each record being representative of an available supply pool of one or more service provider types in one of a plurality of regions, and demand therefor, during the respective predetermined time period; generate, using said supply and demand data, probability data for each of said plurality of regions and supply pools in relation to respective predetermined time periods, said probability data comprising probability values representative of a likelihood of demand associated with respective time slot/supply pool/region combinations; perform a simulation of supply and demand conditions in said plurality of regions by mapping said aggregated supply and demand data to said probability data in a trained forecasting model and generating prediction data for each of said plurality of regions and supply pools, said prediction data being representative of a probability that a service provider will receive a user booking in a specified region within a predetermined period of time; and output said prediction data for display on a service provider communications device.