Touch Event Classification Using Accelerometer Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Touch-sensitive devices often inaccurately register unintentional touch events, such as those caused by a user gripping the device, leading to undesired activations and operations.
Innovation Solution
A system that analyzes touch surface data and accelerometer data to classify touch events as intentional or unintentional, using a classification component to distinguish between different types of contact and proximity, and an operation management component to reject unintentional touch events while enabling intentional ones.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the touch sensitive surface responds to all finger contact, then the device is more responsive to user inputs, but unintentional touch events cause false activations
Solution Approach 1:
The patent introduces an intermediary classification system that processes touch surface data and accelerometer data to determine whether a touch event is intentional or unintentional. This intermediary layer acts as a mediator between the touch sensitive surface and the system response, analyzing multiple data sources (touch coordinates, pressure, accelerometer readings) to make a determination before triggering system actions, thereby reducing false activations while maintaining responsiveness to genuine user inputs
Solution Approach 2:
The patent changes the parameters used for touch event recognition by combining multiple parameters (touch surface data including contact points and pressure, accelerometer data including device orientation and motion) rather than relying on a single parameter. This multi-parameter approach allows the system to distinguish between intentional touches and unintentional contacts based on the pattern and context of the parameters, resolving the contradiction between responsiveness and reliability
2Measurement precision
If the system processes all touch events, then no intentional touches are missed, but unintentional touches waste processing resources
Solution Approach 1:
The patent applies partial action by selectively processing only those touch events that meet certain criteria for being intentional. Rather than processing every touch event equally, the system performs preliminary analysis using accelerometer data and touch patterns to identify promising candidates for further processing, thereby reducing energy consumption while maintaining detection accuracy for genuine user inputs
Solution Approach 2:
The patent replaces a simple mechanical threshold-based touch detection system with a more sophisticated classification system that uses machine learning or rule-based algorithms to analyze touch patterns and accelerometer data. This substitution enables more accurate distinction between intentional and unintentional touches, improving measurement precision while the intelligent filtering reduces unnecessary processing of false events, thereby conserving energy
Data Source
AI summary
Techniques enabling improved classification of touch events associated with a touch sensitive surface of a touch sensitive device and rejection of unintentional touch events associated with the touch sensitive surface are presented. A classification component can analyze touch screen data associated with a touch sensitive surface of a device and sensor data received from an accelerometer, gyroscope, and/or ultrasonic sensor. Based on a result(s) of the analyzing, the classification component can determine a contact classification for an object with respect to the touch sensitive surface, wherein the contact classifications can comprise a classification for a particular intended touch event and a classification for an unintentional touch event, with respect to the touch sensitive surface. In response to detecting an unintentional touch event, an operation management component can reject the unintentional touch event and/or place the display screen of the device in an off state.