Sensor-Context Routine Prediction for GPS-Limited Mobile Assistance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing mobile devices rely on location-based predictions for user assistance, which can be unreliable when GPS signals are weak or unavailable, and require manual user input for venue labeling.
Innovation Solution
A mobile device uses sensor readings to determine context independently of location, recording sensor data as context vectors associated with user actions, allowing it to predict and assist without needing precise geographic information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If location-based prediction methods are used, then predictive user assistance can be provided, but reliability deteriorates when GPS signals are weak or unavailable
Solution Approach 1:
The patent introduces sensor readings (accelerometer, gyroscope, magnetometer, barometer, microphone, camera) as intermediary data sources to bridge the gap when GPS location information is unavailable. These sensors capture contextual information about user actions and environment, enabling prediction continuity without relying solely on location data.
Solution Approach 2:
The system changes the parameters used for prediction from purely location-based (GPS coordinates) to include sensor-based parameters (motion patterns, environmental readings, device orientation). This parameter transformation allows the prediction system to operate reliably in environments where GPS signals are weak or unavailable.
2Measurement precision
If manual user input for venue labeling is required, then prediction accuracy can be improved, but ease of operation deteriorates
Solution Approach 1:
The system performs self-labeling by automatically analyzing sensor readings and user behavior patterns to identify and categorize venues and contexts without requiring manual user input. The device serves itself by generating contextual labels from its own sensor data, eliminating the need for users to manually annotate locations.
Solution Approach 2:
The patent replaces the mechanical process of manual user labeling with an automated sensor-based detection and analysis system. Instead of users physically entering venue information, the system uses sensor data processing and pattern recognition to automatically identify and label contexts, substituting human effort with automated computational processes.
3Adaptability or versatility
If sensor readings are used to determine context, then assistance can be provided without GPS, but device complexity increases
Solution Approach 1:
The patent makes existing mobile device sensors serve multiple functions: they are used for traditional purposes (motion detection, navigation) and simultaneously for contextual prediction and venue identification. This multi-functionality allows the system to operate without GPS while reusing existing hardware components, minimizing the need for additional specialized devices.
Solution Approach 2:
The system merges sensor data processing with the existing prediction framework, combining multiple sensor inputs (accelerometer, gyroscope, magnetometer, barometer, microphone, camera) into a unified contextual model. This integration consolidates complex processing into a cohesive system that leverages existing device architecture rather than adding separate complex subsystems.
Data Source
AI summary
A mobile device can provide predictive user assistance based on various sensor readings, independently of or in addition to a location of the mobile device. The mobile device can determine a context of an event. The mobile device can store the context and a label of the event on a storage device. The label can be provided automatically by the mobile device or by the external system without user input. At a later time, the mobile device can match new sensor readings with the stored context. If a match is found, the mobile device can predict that the user is about to perform the action or recognize that the user has performed the action again. The mobile device can perform various operations, including, for example, providing user assistance, based on the prediction or recognition.