Destination Estimation Using Certainty Threshold Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional destination estimating apparatuses in navigation systems face accuracy issues when estimating destinations based on past locations, as they often include candidates with low certainty factors, leading to incorrect rankings and reduced accuracy.
Innovation Solution
A destination estimating apparatus that includes a history storing unit, a destination estimating unit, a candidate excluding unit, and a model storing unit, which excludes destination candidates with certainty factors below a predetermined threshold and uses a probability model to rank and select high-probability destinations, improving accuracy by focusing on routine and recently visited locations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If all past destination locations are included as destination candidates, then the system can cover more possible destinations, but the estimation accuracy decreases due to inclusion of low-certainty candidates
Solution Approach 1:
The patent extracts and removes low-certainty destination candidates from the candidate list based on a certainty factor calculation. The candidate excluding unit eliminates locations that do not meet the threshold criteria, thereby improving estimation accuracy while maintaining coverage of high-probability destinations.
Solution Approach 2:
The patent applies different quality standards to different destination candidates based on their individual certainty factors. Each candidate is evaluated separately using historical data, situation information, and user information to determine its suitability, rather than applying a uniform inclusion criterion to all candidates.
2Ease of operation
If the system automatically estimates destination without user input, then user convenience is improved, but estimation accuracy may decrease due to incorrect predictions
Solution Approach 1:
The patent incorporates feedback mechanisms by utilizing historical destination data and user information to continuously refine the certainty factor calculation. The system learns from past user behavior patterns and adjusts its estimation criteria, providing improved accuracy while maintaining automatic operation.
Solution Approach 2:
The patent dynamically adjusts the certainty factor threshold and weighting parameters based on historical data analysis. By changing these parameters according to learned user patterns and situation contexts, the system optimizes the balance between automatic convenience and estimation accuracy.
3Measurement precision
If more historical data is used for estimation, then the system can better understand user patterns, but the complexity of processing increases
Solution Approach 1:
The patent extracts only the essential and relevant features from historical data for the certainty factor calculation, rather than processing all available data uniformly. This selective extraction reduces computational complexity while maintaining the ability to identify important user patterns.
Solution Approach 2:
The patent applies different processing depths and analytical methods to different portions of historical data based on their relevance and recency. More recent and frequently occurring patterns receive greater analytical attention, while less relevant historical data is processed more efficiently.
Data Source
AI summary
An object of this invention is to improve the accuracy of estimating a destination in a destination estimating apparatus. A destination estimating apparatus 100 includes: a learning data storing unit 9b that stores a history of a location specified as a destination in the past; a destination estimating unit 83 that estimates a destination from among a plurality of destination candidates including a location stored in the learning data storing unit 9b; and a candidate excluding unit 84 that, based on the history stored in the learning data storing unit 9b, excludes a destination candidate for which it is determined that a certainty factor of being a destination is lower than a predetermined threshold value from destination candidates that are estimated as being a destination by the destination estimating unit 83.