Vehicle Sharing Demand Prediction Through Intent Grouping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional vehicle sharing services overestimate demand, leading to unnecessary vehicle allocation and increased costs and environmental impact due to inefficient demand prediction.
Innovation Solution
A system utilizing intent grouping and demand algorithms to accurately determine user needs by grouping user intents and assigning characteristics to demands, incorporating machine learning for refined intent and demand determination, and optimizing vehicle allocation based on actual user needs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional demand estimation methods are used, then vehicle allocation is increased to ensure coverage, but this leads to over-allocation and unnecessary costs
Solution Approach 1:
The patent replaces conventional mechanical counting methods with machine learning-based intent detection and grouping algorithms. The system analyzes user behavior patterns, search queries, and interaction data to predict actual vehicle demand, substituting simple quantity counting with intelligent prediction models that account for user intent variability and contextual factors.
Solution Approach 2:
The system implements feedback loops where actual vehicle usage data and user behavior patterns are continuously fed back into the demand prediction models. This allows the machine learning algorithms to refine their predictions over time, adjusting vehicle allocation strategies based on real-world performance and user response patterns.
2Adaptability or versatility
If more vehicles are allocated to meet perceived demand, then service coverage is improved, but environmental impact and operational costs increase
Solution Approach 1:
The patent changes the parameters used for demand measurement from simple vehicle request counts to refined metrics based on user intent analysis. By analyzing factors such as search behavior, interaction duration, and contextual patterns, the system transforms raw demand data into more accurate predictions that reflect actual usage needs, thereby optimizing the balance between service coverage and resource consumption.
3Reliability
If demand is overestimated, then vehicle availability is ensured, but this creates waste and increases service costs
Solution Approach 1:
The system applies partial action by allocating vehicles based on predicted actual demand rather than perceived demand. The machine learning models identify and filter out false or excessive demand signals, allowing the system to deploy vehicles only when genuinely needed, thereby avoiding over-allocation and associated waste while maintaining adequate service levels.
Data Source
AI summary
Vehicle sharing service optimization (e.g., using a computerized tool) is enabled. For example, a system can comprise a memory that stores computer executable components, and a processor that executes the computer executable components stored in the memory, wherein the computer executable components comprise: an intent grouping component that, using a defined intent grouping algorithm, groups intents of a user into an intent group, wherein the intents comprise respective requests to schedule an appointment to use a vehicle, a demand component that, based on the intents of the intent group and using a defined demand algorithm, determines a demand of the user, wherein the demand comprises one or more parameters representative of a need, of the user, for the vehicle, and an output component that generates an output representative of the demand.