Touch Display Motion Recognition with Two-Stage Input Validation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Electronic devices struggle to accurately distinguish between different input motions, particularly when multiple touch points of a user interact with the touch display with a time difference, leading to misidentification of swipe motions.
Innovation Solution
A method and electronic device that utilize a first algorithm to identify a valid input based on touch data, followed by a second algorithm to determine input motion through feature extraction, temporal features, and classification, incorporating a queue for storing inference results to confirm consistent input patterns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If coordinate-based recognition method is used to identify swipe motions, then the device can detect touch movement distance variation, but it cannot distinguish between different input motions of the user
Solution Approach 1:
The patent segments the motion recognition process into multiple independent algorithms: a first algorithm that identifies valid inputs based on touch area characteristics, and a second algorithm that determines input motion types. This segmentation allows each algorithm to specialize in specific aspects, improving overall accuracy in distinguishing different input motions while maintaining ease of operation through automated processing
Solution Approach 2:
The patent introduces an intermediary inference result information mechanism that bridges the first and second algorithms. The first algorithm produces inference result information about valid inputs, which then serves as input to the second algorithm for motion type determination. This intermediary layer enables sophisticated motion distinction without requiring a single complex algorithm, resolving the contradiction between operational simplicity and measurement precision
2Adaptability or versatility
If representative coordinate value is used to determine movement distance variation, then the device can process multi-touch inputs, but the device cannot identify the corresponding motion when the representative coordinate disappears
Solution Approach 1:
The patent implements feedback through the first algorithm that continuously monitors touch area characteristics and generates inference result information about valid inputs. This feedback mechanism allows the system to adapt to varying touch patterns and maintain reliable motion identification even when representative coordinates disappear, as the first algorithm provides continuous validation of input validity throughout the motion sequence
Solution Approach 2:
The first algorithm performs preliminary identification of valid inputs before the second algorithm processes motion determination. By pre-validating inputs based on touch area characteristics, the system ensures that only reliable inputs are processed for motion identification, maintaining high reliability even in complex multi-touch scenarios where representative coordinates may disappear
3Measurement precision
If multiple algorithms are combined for input motion identification, then the accuracy of input motion recognition is improved, but the device complexity increases
Solution Approach 1:
The patent divides the complex motion recognition task into two distinct algorithms with clear functional separation: the first algorithm handles valid input identification based on touch area analysis, while the second algorithm handles motion type determination. This segmentation reduces overall complexity by making each algorithm more focused and manageable, while still achieving high accuracy through their coordinated operation
Solution Approach 2:
The inference result information acts as an intermediary that simplifies the interaction between the two algorithms. Instead of requiring complex coordination or shared state management, the first algorithm outputs inference result information that the second algorithm consumes as input. This intermediary mechanism reduces device complexity by creating a clean data flow interface between algorithms while maintaining high recognition accuracy
Data Source
AI summary
A method of identifying an input motion of an electronic device includes identifying, based on touch data of a touch display and a first algorithm, whether a first touch input to the touch display indicates a valid input; obtaining, based on the first touch input indicating the valid input, first inference result information related to the input motion for the first touch input based on the touch data and a second algorithm; and identifying, based on the first inference result information and second inference result information related to the input motion for at least one second touch input, whether the first touch input and the at least one second touch input correspond to the input motion.