Transport-Dependent Destination Prediction via Mode Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current navigation systems require manual input of destinations, which is burdensome and lacks automation in determining the user's intended destination during travel.

Innovation Solution

A destination analysis module that estimates a user's destination by detecting the mode of transportation and using a corresponding model to predict likely destinations based on the partial path taken within a geographic area, employing Bayes analysis to assign probabilities to map location elements.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If manual input of destination is required, then navigation system can provide accurate route guidance, but user burden increases and automation is reduced

Engineering Contradiction:

Improveautomatic destination determinationVSAvoiduser input burden

Core Design Contradiction:

Extent of automationVSEase of operation

Solution Approach 1:

The system automatically determines the user's destination by analyzing transportation mode and path data without requiring manual user input. The destination analysis module infers destination from detected transportation mode (automobile, public transportation, walking) and the partial path taken, making the system self-serve the user's navigation needs

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical interaction of manual destination input with an automated information processing system. Instead of requiring users to type or select destinations, the system uses sensors and algorithms to detect transportation mode and analyze movement patterns to automatically infer destination

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If a single destination prediction model is used, then system complexity is reduced, but prediction accuracy for different transportation modes deteriorates

Engineering Contradiction:

Improvedestination prediction accuracyVSAvoidmodel selection mechanism

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system applies different prediction models tailored to each transportation mode. Instead of using a single generic model, the destination analysis module selects and applies specific models appropriate for automobile travel, public transportation, or walking, optimizing prediction accuracy for each local context or transportation category

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system changes the model parameters based on the detected transportation mode. When the transportation mode is identified (automobile, public transportation, walking), the corresponding model with appropriate parameters for that mode is loaded and applied, allowing the system to adapt its prediction behavior to different travel contexts

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS8538686B2Transport-dependent prediction of destinations

Publication Date: 2013.09.17 MICROSOFT TECHNOLOGY LICENSING LLC

AI summary

A destination analysis module is described which estimates at least one destination of a user given a partial path taken by the user within a geographic area. The destination analysis module operates by detecting a mode of transportation that a user uses to traverse the path (e.g., automobile, public transportation, walking, etc.). The destination analysis module then loads a model associated with the mode of transportation into a destination prediction module and estimates at least one destination based on the path and the model. The model has various components that depend on the mode of transportation, such as routing network information and prior probability information.