Personalized Response Prediction for Mobile Messaging

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Portable electronic devices face challenges in message input due to their small form factors, which result in sub-optimal user interfaces for typing, leading to increased cognitive burden and inefficiency.

Innovation Solution

The development of techniques for predicting a user's likely response to an incoming message and presenting these predictions for user selection, reducing the need for manual input and enhancing the efficiency of the human-machine interface.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If manual typing is used on reduced-size keyboards, then message input can be achieved, but user cognitive burden increases and typing efficiency decreases

Engineering Contradiction:
Improvetyping efficiencyVSAvoidcognitive burden
Core Design Contradiction:
ProductivityVSEase of operation

Solution Approach 1:

The system performs preliminary actions by analyzing conversation history, context attributes, and user behavior patterns beforehand to generate predicted response suggestions before the user needs to type. This allows the most likely responses to be prepared in advance, reducing the user's typing burden and cognitive load during actual message composition.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system serves itself by automatically generating and updating personalized prediction models based on user interaction data without requiring manual configuration. The machine learning model continuously learns from user responses and conversation patterns, automatically improving prediction accuracy over time while reducing the need for user intervention in system setup and maintenance.

Inventive Principle:
Principle #25Self-service

2Ease of operation

If more keyboard space is allocated for typing, then typing comfort improves, but device form factor increases

Engineering Contradiction:
Improvetyping comfortVSAvoiddevice form factor
Core Design Contradiction:
Ease of operationVSArea of moving object

Solution Approach 1:

The patent replaces the mechanical typing system with an intelligent prediction system that uses machine learning algorithms and natural language processing. Instead of relying on physical keyboard space and manual typing mechanics, the system substitutes computational processes that analyze context and generate predictions, effectively eliminating the need for large keyboard layouts while maintaining or improving typing comfort.

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

3Measurement precision

If personalized prediction models are trained with extensive user data, then prediction accuracy improves, but processing power and time requirements increase

Engineering Contradiction:
Improveprediction accuracyVSAvoidprocessing power
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The system applies local quality by training and maintaining specialized prediction models for different contexts such as different conversation partners, message types, and communication scenarios. Instead of using a single monolithic model that processes all data uniformly, the system creates context-specific models that focus computational resources on relevant patterns, improving prediction accuracy for each context while reducing overall processing requirements.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The system performs preliminary data processing and feature extraction during data collection phases, preparing training data in advance to reduce computational burden during model training and inference. By preprocessing conversation data, extracting relevant features, and organizing training datasets beforehand, the system reduces the processing power and time required for actual model training and prediction generation.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3295281B1Personalized prediction of responses for instant messaging
Publication Date: 2024.06.26 APPLE INC
  • EP3295281B1 patent drawingFigure 1A
  • EP3295281B1 patent drawingFigure 1B
  • EP3295281B1 patent drawingFigure 2

AI summary

At an electronic device with a display screen, display a message transcript, where the message transcript includes an incoming message. Determine, based at least in-part on the message, a plurality of suggested one or more characters. Determine if the user of the device has, in the past, frequently inputted a response different from the plurality suggested one or more characters when the plurality were presented for user selection. Optionally, determine if the frequently inputted response is synonymous with a suggested one or more characters. Display the frequently-inputted response, in place of at least one of the plurality of suggested one or more characters, under some circumstances based on these determination(s).