Probability-Based Input Recognition for Small Keyboards
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Data entry on small keyboards or touch screens often results in unintended key presses due to the size of keys relative to human fingers or user error, leading to mistakes in input data.
Innovation Solution
A probability-based method is implemented where each key on the keyboard is associated with a predetermined probability distribution, allowing for the calculation of the likelihood of intended input based on the sequence of entered keys, using a probability matrix to model user input and correct for errors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of moving object
If the keyboard keys are made smaller to fit more keys, then the keyboard density increases, but the user accuracy in pressing the intended key decreases
Solution Approach 1:
A probability distribution model acts as an intermediary between the physical key press event and the intended input. When a user presses a key, the system uses the probability distribution associated with that key to determine the most likely intended input, especially when the pressed key is ambiguous or incorrect due to small key size. This mediator resolves the contradiction by translating physical input into intended input through probabilistic reasoning.
Solution Approach 2:
The system changes the parameter of key association from a one-to-one mapping to a one-to-many probabilistic mapping. Each key is associated with a probability distribution over possible intended inputs, allowing the system to account for the uncertainty introduced by small key sizes. This parameter change enables accurate input recognition despite the reduced key area.
2Measurement precision
If the probability distribution model is made more complex to improve accuracy, then the recognition accuracy improves, but the computational complexity increases
Solution Approach 1:
The probability distributions for each key are pre-computed and stored before use. These distributions are derived from statistical analysis of typing patterns and are saved in advance, so that during actual input recognition, the system only needs to retrieve and apply the pre-computed distributions rather than performing complex calculations in real-time. This preliminary action reduces computational complexity during operation while maintaining high accuracy.
Data Source
AI summary
A method for entering keys in a small key pad is provided. The method comprising the steps of: providing at least a part of keyboard having a plurality of keys; and predetermining a first probability of a user striking a key among the plurality of keys. The method further uses a dictionary of selected words associated with the key pad and/or a user.