Predictive Response Generation for Small Keyboard Typing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The small form factors of portable electronic devices present user interface challenges due to reduced-size keyboards, which are sub-optimal for typing, exacerbated by advancements in electronics packaging that reduce keyboard space, leading to difficulties in efficient message input during message-based communication.

Innovation Solution

The implementation of techniques that predict a user's likely response to an incoming message and present predictions for user selection, reducing the need for manual input by suggesting content based on attributes of selected ideograms, such as emojis, to create a more efficient human-machine interface.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Volume of moving object

If reduced-size keyboards are used to accommodate smaller device form factors, then device portability is improved, but typing efficiency and user input ease deteriorate

Engineering Contradiction:
Improvedevice form factorVSAvoidtyping efficiency
Core Design Contradiction:
Volume of moving objectVSEase of operation

Solution Approach 1:

The system performs preliminary action by automatically generating and presenting predicted response options to the user before the user needs to type. The predictive text system analyzes incoming messages and pre-computes likely responses, so when the user needs to reply, they can simply select from pre-generated options rather than typing from scratch, thus resolving the contradiction between small device size and typing efficiency.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The predictive text system enables self-service by allowing the system to automatically generate response suggestions based on the conversation context and user preferences. The system serves itself by using its own resources (processing power, stored data) to create helpful response options, reducing the burden on the user to manually type messages on a small keyboard.

Inventive Principle:
Principle #25Self-service

2Ease of operation

If more keyboard space is allocated to improve typing efficiency, then user input ease is improved, but device portability deteriorates

Engineering Contradiction:
Improvetyping efficiencyVSAvoiddevice form factor
Core Design Contradiction:
Ease of operationVSVolume of moving object

Solution Approach 1:

The patent applies mechanics substitution by replacing the mechanical keyboard typing process with an automated computational system. Instead of relying on physical keyboard interaction, the system uses algorithms to predict and generate response text, which is then presented to the user for selection. This substitutes the mechanical typing action with an automated information processing approach, maintaining typing efficiency without requiring additional physical keyboard space.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

3Productivity

If predictive text suggestions are implemented to reduce manual input, then user interface efficiency is improved, but processing power requirements increase

Engineering Contradiction:
Improveuser interface efficiencyVSAvoidprocessing power
Core Design Contradiction:
ProductivityVSPower

Solution Approach 1:

The system applies partial action by not generating all possible responses, but only the most likely predictions based on contextual analysis. The predictive text system calculates probability scores for different response options and selectively generates only the top suggestions, rather than exhaustively computing all potential replies. This partial approach maintains user interface efficiency while reducing unnecessary processing power consumption.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS11048873B2Emoji and canned responses
Publication Date: 2021.06.29 APPLE INC
  • US11048873B2 patent drawing
  • US11048873B2 patent drawing
  • US11048873B2 patent drawing

AI summary

At an electronic device, detect a first input on the touch-sensitive surface that represents selection of a first ideogram. Identify at least one attribute of the first ideogram. Select a plurality of suggested one or more characters to display, where at least a first set of suggested one or more characters is selected based on a set of selection criteria, the set of selection criteria including the identified at least one attribute of the first ideogram. Display at least the first set of suggested one or more characters. Detect a second input on the touch-sensitive surface that represents selection of the displayed first set of suggested one or more characters. In response to detecting the second input, displaying a composed electronic message, the composed electronic message including the first ideogram and the selected first set of suggested one or more characters.