Predictive Text Scoring Using Typing Speed and String Length
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Character input on touchscreens, especially for long messages, is cumbersome due to the small screen area and existing predictive text solutions do not effectively utilize typing speed and string length to improve input efficiency.
Innovation Solution
A method that generates predicted strings based on input, assigns scores considering typing speed and string length, and displays the most likely intended string to enhance text input speed and reduce processing cycles, allowing for faster and more accurate typing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If predictive text solutions are implemented on touchscreen devices, then text input efficiency is improved, but the small touchscreen area limits the display of multiple prediction variants
Solution Approach 1:
The patent applies local quality by displaying a different number of predicted strings based on the specific input context and device characteristics. Rather than uniformly displaying a fixed number of predictions, the system adapts the display quantity locally according to the input situation, allowing optimal use of the limited touchscreen area while maintaining high text input efficiency.
2Measurement precision
If multiple predicted strings are displayed to improve prediction accuracy, then processing cycles increase and power consumption rises
Solution Approach 1:
The patent implements partial action by displaying only a selective subset of predicted strings rather than all possible predictions. The system calculates multiple predictions but selectively displays only those that meet certain criteria (such as relevance threshold or contextual importance), thereby reducing processing cycles and power consumption while maintaining sufficient prediction accuracy for the user's needs.
3Productivity
If typing speed is used as a factor for prediction scoring, then input efficiency is improved, but the complexity of the prediction algorithm increases
Solution Approach 1:
The patent applies parameter changes by incorporating typing speed as a dynamic parameter in the prediction scoring mechanism. The system monitors the user's typing speed and adjusts the scoring of predicted strings based on this parameter, allowing faster typists to receive more aggressive predictions while maintaining accuracy for slower typists. This approach improves input efficiency by adapting to user behavior without requiring fundamentally complex algorithmic changes.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method that includes receiving an input, determining, by the processor, a likelihood that a predicted string associated with the received input matches an intended input string, where the determination is a function of at least one of a length of the predicted string and a typing speed associated with the received input, and displaying the predicted string.