Candidate Input Prediction Interface for Mobile Text Entry
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current mobile devices' text prediction functions provide limited options and do not allow users to request specific types of predictions, such as punctuations or categories like verbs or nouns, leading to user frustration and increased typing time due to the small keyboard size.
Innovation Solution
Implementing a user interface that allows users to enter a sentence-generating mode, inhibiting the virtual keyboard and displaying a larger set of candidate inputs, including synonyms and conjugations, based on user gestures or eye tracking, to enhance prediction accuracy and user selection efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Volume of moving object
If a small virtual keyboard is used in mobile devices, then the device size is reduced, but the text input time increases and error rate increases
Solution Approach 1:
The system automatically generates and displays candidate inputs based on the user's current input, allowing the device to serve itself by predicting what the user wants to type next. This reduces the manual typing burden while maintaining a compact keyboard layout.
Solution Approach 2:
The patent replaces the mechanical typing process with an automated prediction system that uses algorithms to generate candidate inputs. Instead of manually selecting from limited keyboard options, the system substitutes mechanical finger typing with automated text generation and display of predicted candidates.
2Ease of operation
If traditional text prediction is implemented, then some prediction functionality is provided, but the number of prediction options is limited and user-specific prediction types cannot be requested
Solution Approach 1:
The system dynamically adjusts the candidate input display based on user interactions. When users swipe through candidate inputs, the system adapts by displaying additional candidate inputs or different types of predictions (such as synonyms, related words, or contextual suggestions), making the prediction system flexible and responsive to user needs.
Solution Approach 2:
The system incorporates feedback mechanisms where user swiping actions on candidate inputs trigger subsequent predictions. The feedback from user selection or rejection of candidates refines future predictions, and the system responds by providing different categories of candidate inputs (verbs, nouns, punctuations) based on user preferences and behavior patterns.
Data Source
AI summary
In certain embodiments, presentation of candidate inputs may be facilitated based on a user interface location of a related candidate input. In some embodiments, a text input may be obtained via a user interface (e.g., via a virtual keyboard). A first candidate input related to the text input may be presented at a first location of the user interface. A first user selection with respect to the first candidate input may be obtained, and a candidate input set related to the first candidate input may be presented on the user interface based on the first user selection. As an example, the candidate input set may be presented such that a second candidate input is presented closer to the first location than a third candidate input based on the second candidate input being associated with a higher likelihood of being selected by a user than the third candidate input.