Touch Point Screening for Low-Load Knuckle Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for invoking knuckle recognition algorithms on electronic devices result in excessive system load and false recognition due to frequent invocation during non-knuckle operations, degrading user experience.
Innovation Solution
A touch operation processing method that determines the number of touch points and capacitance data to generate an identifier, deciding whether to invoke the knuckle recognition algorithm, thereby filtering non-knuckle operations and reducing unnecessary algorithm invocations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the knuckle recognition algorithm is invoked for each screen touch operation, then the user experience is improved by meeting user demands for knuckle function, but the system basic load is severely increased
Solution Approach 1:
The patent applies preliminary action by performing feature extraction and initial judgment on touch operations before invoking the knuckle recognition algorithm. The system pre-processes touch data to identify characteristics (such as touch location, pressure, duration) that can predict whether a knuckle operation is likely to occur, thereby avoiding unnecessary algorithm invocations and reducing system load while maintaining user experience.
Solution Approach 2:
The patent introduces an intermediary layer between the touch operation detection and the knuckle recognition algorithm. This intermediary component analyzes touch features and generates judgment results that determine whether the algorithm should be invoked. This mediator filters out non-knuckle operations before they reach the recognition algorithm, reducing computational burden while preserving the ability to accurately recognize knuckle functions when they occur.
2Reliability
If the knuckle recognition algorithm is invoked for each screen touch operation, then knuckle operations can be recognized, but false recognition increases affecting user experience
Solution Approach 1:
The patent applies preliminary action by performing feature extraction and initial judgment on touch operations before invoking the knuckle recognition algorithm. The system pre-processes touch data to identify characteristics (such as touch location, pressure, duration) that can predict whether a knuckle operation is likely to occur, thereby avoiding unnecessary algorithm invocations and reducing system load while maintaining user experience.
Solution Approach 2:
The patent introduces an intermediary layer between the touch operation detection and the knuckle recognition algorithm. This intermediary component analyzes touch features and generates judgment results that determine whether the algorithm should be invoked. This mediator filters out non-knuckle operations before they reach the recognition algorithm, reducing computational burden while preserving the ability to accurately recognize knuckle functions when they occur.
Data Source
Figure 1A(1)~1A(2)
Figure 1B(1)~1B(2)
Figure 2
AI summary
This application provides a touch operation processing method, a device, and a storage medium. In this method, when a touch operation is received, it is determined, by determining a number of touch points, in other words, based on a touch area, whether to filter the touch operation. When it is determined that the touch operation is a non-knuckle operation that needs to be filtered, an electronic device is set to not invoke a knuckle recognition algorithm. This can avoid invoking the knuckle recognition algorithm for each touch operation, thereby reducing occupation of system resources, and reducing system load.