Touch Screen Panel Input Type Classification and Error Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users often experience confusion between force touch and long touch inputs on touch screen panels due to overlapping pressure and duration conditions, leading to errors in touch type determination.
Innovation Solution
An electronic device with a processor that determines the type of touch input (force touch or long touch) based on coordinates, time, and area, and corrects the touch type determination by analyzing user behavior, updating a touch type model to reduce classification errors and provide accurate user interfaces.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If touch type determination is based on fixed pressure and duration thresholds, then the classification rule is simple, but classification errors occur when user behavior overlaps between force touch and long touch
Solution Approach 1:
The patent applies dynamics by transitioning from fixed static thresholds to dynamic adaptive thresholds. The classification model is continuously updated based on individual user behavior patterns, allowing the pressure and duration thresholds to adapt dynamically to each user's unique interaction style, thereby resolving the contradiction between simple rules and accurate classification
Solution Approach 2:
The patent changes the parameters of the classification system by introducing machine learning models that adjust pressure and duration thresholds based on user behavior data. Instead of using fixed parameters, the system learns optimal parameter values for each user, improving classification accuracy while maintaining operational simplicity through automated adaptation
2Measurement precision
If a machine learning model is introduced to improve touch type determination accuracy, then classification accuracy improves, but system complexity increases
Solution Approach 1:
The patent applies self-service by enabling the system to automatically train and update its own classification model using user behavior data. The machine learning model performs self-adjustment without requiring external intervention or complex manual configuration, reducing the perceived system complexity while maintaining high classification accuracy through automated learning
Solution Approach 2:
The patent implements feedback mechanisms where the system continuously monitors user interactions with the UI elements and uses this feedback to refine the classification model. This closed-loop feedback system automatically improves accuracy over time while keeping the user interface simple, as the complexity is handled autonomously by the learning system
3Ease of operation
If the system outputs UI elements based on determined touch type, then user interaction is enabled, but additional user behavior is required to confirm correct classification
Solution Approach 1:
The patent applies preliminary action by pre-training the classification model with user behavior data before actual touch classification occurs. The system performs preliminary learning during idle periods or initial usage, so that when touch classification is needed, the model is already optimized for that specific user, enabling accurate classification without requiring additional confirmation steps
Solution Approach 2:
The system performs self-validation by automatically monitoring whether the output UI elements receive expected user interactions. If the classified touch type leads to appropriate user behavior (e.g., selection window for long touch, volume adjustment for force touch), the system confirms the classification correctness autonomously without requiring explicit user verification, thus reducing time loss
Data Source
AI summary
An electronic device and a method of operating the same are provided. The electronic device includes a touch screen, and at least one processor configured to determine, as any one of a first touch type or a second touch type, a type of a user input inputted on the touch screen, output a user interface (UI) corresponding to the first touch type based on the type of inputted touch being determined as the first touch type, correct the determined type as the second touch type based on an error being determined to be present in determining the type of inputted touch as the first touch type, and output a UI corresponding to the second touch type.