In-Context Word Prediction Keyboard Interface
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing predictive text input methods for electronic devices require users to divert attention from the keyboard, leading to inefficiencies and eye strain, as they need to focus on suggested words displayed elsewhere on the screen, and often fail to provide contextual understanding for predictions.
Innovation Solution
A method that displays predicted words and future predictions on the same screen as the keyboard, allowing users to select and confirm multiple words without leaving the keyboard, using a predictive algorithm that generates candidate predictions based on current input and contextual data, and accepts selections through continuous touch inputs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If predictive text suggestions are displayed on a separate area of the screen, then users can see predicted words, but users must divert attention from the keyboard causing eye strain and reduced input efficiency
Solution Approach 1:
The patent merges the prediction display area with the keyboard area by displaying predicted words directly within the keyboard interface. The suggestions are shown in contextual positions near where they would naturally appear in the text flow, allowing users to select predictions without moving their eyes away from the keyboard typing area.
Solution Approach 2:
The patent utilizes the vertical dimension of the touchscreen by displaying predicted words in overlapping or adjacent vertical spaces within the keyboard area. Multiple predictions are arranged in layers or columns that fit within the existing keyboard footprint, effectively using unused vertical space to display information without expanding the horizontal footprint that would require eye movement.
2Reliability
If users must select predicted words by moving to a different display area, then predictions can be selected, but text input speed and efficiency are reduced
Solution Approach 1:
The patent displays multiple predicted words in advance within the keyboard area, allowing users to see and select from several options simultaneously without needing to navigate to a separate selection screen. The predictions are pre-positioned in easily accessible locations within the keyboard interface, enabling immediate selection without interrupting the typing flow.
Solution Approach 2:
The system provides immediate visual feedback by highlighting and displaying predicted words directly in the keyboard area as the user types. The predictions update in real-time based on the current input, and the interface provides clear visual cues about which words are predicted and how to select them, enabling fast and accurate word selection without requiring users to divert attention.
3Area of stationary object
If the touchscreen area is small, then the device is compact and portable, but text input becomes cumbersome and difficult
Solution Approach 1:
The patent makes the keyboard area multi-functional by using it both for typing and for displaying predicted words. The same touchscreen real estate serves dual purposes: as the typing interface and as the prediction display area. This eliminates the need for separate dedicated prediction display space, allowing compact devices to maintain efficient text input capabilities.
Solution Approach 2:
The patent implements a dynamic keyboard interface where the display of predicted words adapts based on the current typing context. The predictions appear and disappear dynamically as the user types, and their positions and visibility adjust based on the current input state. This dynamic behavior allows the interface to provide rich prediction information without requiring permanent allocation of additional screen space.
Data Source
AI summary
Methods and systems for predicting user input on a keyboard. Methods include enabling user input on a display comprising at least three fields. The first field displays an input string that is based on input selections such as keyboard entries. The second field displays a candidate prediction generated based on other input selections, consisting at least in part of a proposed completion to the input selection, and partially based on the input string in the first field. The third field displays another candidate prediction generated based on the input string in the first field as well as the candidate prediction in the second field.