Personalized ETA Prediction Using Anonymized Driving Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing ETA services provide non-personalized estimates to users, failing to account for individual driving habits, tendencies, and vehicle conditions, leading to inaccurate travel time predictions.
Innovation Solution
A method and system that collect and analyze user-specific driving data, along with real-time ETA information, to determine personalized parameters for a mapping function, providing a tailored ETA while preserving user privacy through anonymization techniques.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If ETA information is estimated without user-specific data, then the service can be provided to multiple users with the same information, but the accuracy and personalization of ETA predictions deteriorate
Solution Approach 1:
The system performs preliminary actions by collecting and storing user-specific driving data (actual driving times, routes, preferences) before ETA prediction is needed. This pre-collected data is then used to personalize ETA estimates, improving accuracy without adding complexity during the actual prediction moment.
Solution Approach 2:
The system creates a simplified copy or representation of user behavior patterns through the mapping function with personalized parameters. Instead of processing complex raw driving data every time, the system uses learned parameters that capture essential user characteristics, reducing computational complexity while maintaining prediction accuracy.
2Measurement precision
If user-specific driving data is collected and analyzed, then personalized ETA accuracy improves, but user privacy and data security risks increase
Solution Approach 1:
The system extracts only the essential parameters needed for personalization from complete user driving data. By separating and using only the necessary features (driving patterns, preferences) while excluding sensitive personal information, the system achieves personalization without exposing unnecessary user data.
Solution Approach 2:
The mapping function serves as an intermediary that processes user driving data and transforms it into personalized ETA predictions without exposing raw user data. This intermediary layer allows the system to utilize user-specific information for accuracy while protecting user privacy by not directly handling or storing sensitive personal data.
3Adaptability or versatility
If the same ETA information is provided to all users, then the system operation is simple and fast, but the adaptability to individual driving behaviors is lost
Solution Approach 1:
The system applies local quality by providing different ETA estimates tailored to each user's specific driving patterns, preferences, and vehicle characteristics. Instead of a uniform approach for all users, the system customizes predictions locally for each user based on their unique data, improving adaptability without requiring complete system redesign.
Solution Approach 2:
The system achieves adaptability through parameter changes in the mapping function. By adjusting the parameters of the ETA prediction model based on user-specific driving data, the system can adapt to individual behaviors while maintaining the same underlying prediction framework, thus managing complexity effectively.
Data Source
AI summary
The disclosure is directed to improving driving experience by determining and providing a personalized estimated time of arrival (ETA). For example, using at least one computing device, driving data associated with a user may be collected and stored in memory. The at least one computing device may also be used to receive ETA-related data including one or more real time ETA estimations, perform analysis on one or more of the driving data and the ETA-related data so as to determine a set of personalized parameters of a mapping function that correspond to a training set. The at least one computing device may also be used to determine the personalized ETA based at least in part on the determined set of personalized parameters and provided to the user.