Predictive Text Ranking Using Typing Speed and Confidence

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Character input on touchscreens, particularly in electronic devices like smartphones and tablets, is cumbersome due to the small screen size, especially when entering long messages, as existing predictive text solutions do not effectively account for typing speed and confidence to improve input efficiency.

Innovation Solution

A method that generates and ranks predicted strings based on the input string, considering whether it is a substring and factors like typing speed and confidence, to display the most likely intended input, allowing for faster and more accurate text input by suggesting completions or corrections.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If predictive text solutions are implemented on touchscreen devices, then text input efficiency should improve, but the small touchscreen area makes character input cumbersome

Engineering Contradiction:

Improvetext input efficiencyVSAvoidcharacter input ease

Core Design Contradiction:

ProductivityVSEase of operation

Solution Approach 1:

The system automatically analyzes typing patterns, speed, and confidence to generate and rank predicted strings without requiring user intervention. The processor monitors input patterns and autonomously provides predicted completions, allowing the system to serve itself in improving input efficiency while compensating for the small touchscreen area.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system performs preliminary analysis of typing patterns and generates predicted strings before the user completes their input. By ranking predicted strings based on typing speed and confidence metrics in advance, the system prepares suggestions that are ready for immediate selection, reducing the effort required during actual character input.

Inventive Principle:

Principle #10Preliminary action

2Measurement precision

If existing predictive text solutions are used, then some input assistance is provided, but they do not effectively account for typing speed and confidence

Engineering Contradiction:

Improveprediction accuracyVSAvoidprediction system complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system continuously monitors typing patterns, speed, and confidence as feedback mechanisms. This feedback is used to dynamically adjust and refine the ranking of predicted strings, improving prediction accuracy by adapting to the user's specific typing behavior while managing complexity through systematic data collection and analysis.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system changes the parameters used for prediction by incorporating typing speed and confidence metrics alongside traditional predictive text algorithms. This multi-parameter approach improves prediction accuracy by considering multiple dimensions of user input behavior, while the structured method of integrating these parameters helps manage system complexity.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS9063653B2Ranking predictions based on typing speed and typing confidence

Publication Date: 2015.06.23 MALIKIE INNOVATIONS LTD

AI summary

A method that includes receiving an input string, ranking, by the processor, a predicted string associated with the input string, wherein the ranking depends on whether the input string is a substring of the predicted string and at least on one of a typing speed and a typing confidence, and displaying the ranked predicted string.